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

    Neuronpedia

    INDEX
    Explanations

    Pré-calculadas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    1.23
    en
    0.98
    a
    0.93
    0.86
    este
    0.83
    aff
    0.82
    é
    0.81
    ares
    0.79
    endpoints
    0.79
    per
    0.78
    POSITIVE LOGITS
     volna
    1.00
     ///<
    0.89
     opined
    0.85
    -(\
    0.82
    BeforeCall
    0.79
    raient
    0.79
     olisi
    0.79
    ޗ
    0.77
    ਸੀਂ
    0.77
     astray
    0.76
    Act Density 0.000%

    No Known Activations