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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    This neuron is triggered by the word “use,” especially when asking how to use something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traced
    -0.07
     Cbd
    -0.07
     ith
    -0.07
    (Math
    -0.06
    -change
    -0.06
     Bio
    -0.06
    ix
    -0.06
    .cn
    -0.06
     гол
    -0.06
     BW
    -0.06
    POSITIVE LOGITS
    _setopt
    0.07
     تجاری
    0.07
    ahren
    0.07
     wichtig
    0.06
     neben
    0.06
    _neurons
    0.06
    intersect
    0.06
     adj
    0.06
     اینتر
    0.06
    注意
    0.06
    Act Density 0.030%

    No Known Activations