Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Quantities and measurements

    np_max-act · gemini-2.0-flash

    details related to packaging and manufacturing processes, specifically for products like filter bags.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on quantitative expressions, detecting numeric measurements and related unit or count terms (e.g. “number,” “seconds,” “time,” “distance,” “predetermined”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    general
    -0.06
     Tell
    -0.06
    더니
    -0.06
    _GENERAL
    -0.06
    DOT
    -0.06
     Door
    -0.06
    MLE
    -0.06
     Thinking
    -0.06
     تغییر
    -0.06
    wn
    -0.06
    POSITIVE LOGITS
    ifar
    0.06
     swath
    0.06
     disob
    0.06
     designs
    0.06
     getTime
    0.06
    (numbers
    0.06
     expectancy
    0.06
     constr
    0.06
     Bayesian
    0.06
     somewhat
    0.06
    Act Density 0.040%

    No Known Activations