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

    Neuronpedia

    INDEX
    Explanations

    sports news

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out verbs—especially finite and modal verb forms—throughout the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cotton
    -0.07
    爱
    -0.06
    anz
    -0.06
     cheaper
    -0.06
    έα
    -0.06
     broader
    -0.06
    rá
    -0.06
    ermann
    -0.06
    osto
    -0.06
     metre
    -0.06
    POSITIVE LOGITS
    _TYP
    0.06
    :@"%@
    0.06
     leth
    0.06
    .Dropout
    0.06
    Advance
    0.06
    JSONObject
    0.06
    orderId
    0.06
     Advance
    0.06
    .startDate
    0.06
    .protocol
    0.06
    Act Density 0.043%

    No Known Activations