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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    This neuron responds primarily to named-entity tokens (the “NAME_…” placeholders).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Input
    -0.07
    営
    -0.06
    """,↵
    -0.06
    /********
    -0.06
    HttpResponse
    -0.06
    alizace
    -0.06
     programmers
    -0.06
    ****************************************************************
    -0.06
     serum
    -0.06
    托
    -0.06
    POSITIVE LOGITS
    Ｂ
    0.06
     sır
    0.06
     Master
    0.06
     than
    0.06
    isphere
    0.06
     bilgi
    0.06
    inalg
    0.06
     Bez
    0.06
    requested
    0.06
    _HEIGHT
    0.05
    Act Density 0.019%

    No Known Activations