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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eleven
    -0.07
     honorary
    -0.06
    353
    -0.06
    larla
    -0.06
     목록
    -0.06
     fram
    -0.06
    89
    -0.06
    911
    -0.06
     Sov
    -0.06
     Wilde
    -0.06
    POSITIVE LOGITS
    imientos
    0.07
    ど
    0.07
    .gms
    0.07
    imal
    0.07
    Y
    0.07
     enzymes
    0.06
     absurd
    0.06
    imiento
    0.06
    кость
    0.06
    blem
    0.06
    Act Density 0.016%

    No Known Activations