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

    Neuronpedia

    INDEX
    Explanations

    remote work

    np_max-act · gemini-2.0-flash

    The neuron identifies numbered list items and their associated content—i.e. it fires on tokens forming “1. …”, “2. …”, etc., and the words that follow them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ПК
    -0.08
    .showMessage
    -0.07
     NGC
    -0.07
    />.
    -0.07
     Indicator
    -0.07
     구
    -0.07
     obligation
    -0.06
     дод
    -0.06
     impossible
    -0.06
    やす
    -0.06
    POSITIVE LOGITS
    .sp
    0.06
    (comm
    0.06
    /validation
    0.06
    queries
    0.06
    .BUTTON
    0.06
    ritt
    0.06
     dye
    0.06
    .Flush
    0.06
     заст
    0.06
     pourrait
    0.06
    Act Density 0.024%

    No Known Activations