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

    Neuronpedia

    INDEX
    Explanations

    Ре

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    1.15
     While
    0.97
    ты
    0.95
     to
    0.95
     so
    0.94
     workings
    0.94
     while
    0.93
    ながら
    0.89
    ความเป็น
    0.89
     of
    0.89
    POSITIVE LOGITS
    ON
    1.09
    टी
    0.91
    OL
    0.87
    ol
    0.85
    oscill
    0.84
    el
    0.82
    razione
    0.82
    an
    0.78
    िले
    0.78
    stilling
    0.78
    Act Density 0.006%

    No Known Activations