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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects the start of a “product features” section, marked by the Chinese label “产品卖点” (and associated bracket “[”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .disabled
    -0.07
    Yang
    -0.07
     bols
    -0.06
    typed
    -0.06
    ्प
    -0.06
     tenth
    -0.06
    所以
    -0.06
    344
    -0.06
     Almost
    -0.06
    bate
    -0.06
    POSITIVE LOGITS
     başar
    0.07
    _bitmap
    0.07
     отмет
    0.06
    _ctrl
    0.06
     Law
    0.06
     провести
    0.06
     big
    0.06
    ync
    0.06
    níka
    0.06
     JQuery
    0.06
    Act Density 0.046%

    No Known Activations