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

    Neuronpedia

    INDEX
    Explanations

    instructions and documentation

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive (“dead”) and does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SHA
    -0.07
     scram
    -0.06
    emain
    -0.06
     Fran
    -0.06
     garbage
    -0.06
     Vir
    -0.06
    eview
    -0.06
     shaped
    -0.06
    -Version
    -0.06
     Belle
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵
    0.07
    jr
    0.07
     погод
    0.07
     lawyers
    0.07
    -elected
    0.06
    输出
    0.06
    ілля
    0.06
    uyền
    0.06
    เคราะห
    0.06
    ランド
    0.06
    Act Density 0.010%

    No Known Activations