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

    Neuronpedia

    INDEX
    Explanations

    Probability calculations

    np_max-act · gemini-2.0-flash

    probability calculations related to picking letters without replacement.

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

    The neuron strongly activates on numeric tokens—especially decimal numbers representing probabilities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ubuntu
    -0.07
     eos
    -0.06
     CEL
    -0.06
    мот
    -0.06
     inve
    -0.06
    mandatory
    -0.06
    apl
    -0.06
    FilterWhere
    -0.06
    لى
    -0.06
    forums
    -0.06
    POSITIVE LOGITS
    uries
    0.06
     urls
    0.06
     LSD
    0.06
    .readInt
    0.06
    ／/
    0.06
    OTTOM
    0.06
     raping
    0.06
    .surface
    0.06
     petrol
    0.06
    /*↵
    0.06
    Act Density 0.005%

    No Known Activations