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

    Neuronpedia

    INDEX
    Explanations

    code, comments, and specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -2.31
    us
    -1.70
    ti
    -1.65
     {
    -1.64
    },
    -1.56
    is
    -1.55
     no
    -1.54
    他也
    -1.52
     \
    -1.49
     —
    -1.48
    POSITIVE LOGITS
    ↵
    1.89
     recientemente
    1.88
    1.84
    ть
    1.80
     hauptsächlich
    1.78
     BOTH
    1.73
     aquellas
    1.70
    튿
    1.69
     Jeśli
    1.69
     píše
    1.68
    Act Density 0.000%

    No Known Activations