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

    Neuronpedia

    INDEX
    Explanations

    orders, logs, texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.98
     The
    0.81
     Как
    0.81
    m
    0.79
    rées
    0.79
     Pada
    0.78
    rée
    0.78
     Responsible
    0.77
     music
    0.76
     والإ
    0.74
    POSITIVE LOGITS
    weird
    0.94
     наличии
    0.92
    それで
    0.81
    型号
    0.79
    ToLower
    0.79
    INVALID
    0.78
     gehad
    0.78
     Zusatz
    0.78
    UTF
    0.77
    を買
    0.77
    Act Density 0.309%

    No Known Activations