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

    Neuronpedia

    INDEX
    Explanations

    Acronyms/initialisms

    np_max-act · gemini-2.0-flash

    This neuron activates on the uppercase token “INT” (as in the abbreviation “INTL”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ame
    -0.07
    ****************************************************************
    -0.06
     heaters
    -0.06
     notas
    -0.06
     sunt
    -0.06
    avanaugh
    -0.06
     valve
    -0.06
     boasted
    -0.06
    Erro
    -0.06
     harvested
    -0.06
    POSITIVE LOGITS
    _PERMISSION
    0.07
    _jet
    0.06
    <Member
    0.06
    BuildContext
    0.06
    Ｉ
    0.06
    MC
    0.06
    Ệ
    0.06
    _OC
    0.06
     ilk
    0.06
    KC
    0.06
    Act Density 0.172%

    No Known Activations