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

    Neuronpedia

    INDEX
    Explanations

    word boundary `\b`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manuscript
    2.10
     favore
    1.94
    izable
    1.87
     omission
    1.85
    ativo
    1.77
    و
    1.74
     ì
    1.73
    >>;
    1.70
     वापसी
    1.67
    idity
    1.66
    POSITIVE LOGITS
    sqrt
    2.35
    a
    1.97
    iť
    1.93
    ปี
    1.84
    એ
    1.83
     tasked
    1.83
     meios
    1.82
    녕하
    1.80
    iezan
    1.79
    ए
    1.75
    Act Density 0.000%

    No Known Activations