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

    Neuronpedia

    INDEX
    Explanations

    requesting something from me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.02
    ن
    0.86
    soever
    0.76
    ่
    0.75
    կ
    0.75
    тся
    0.74
     écrite
    0.73
    ې
    0.73
    به
    0.73
    T
    0.70
    POSITIVE LOGITS
    gb
    0.85
    最具
    0.82
    МО
    0.81
    𝘭
    0.80
    il
    0.79
    ushing
    0.79
    punten
    0.79
    enn
    0.77
    ΜΑ
    0.77
    मारी
    0.76
    Act Density 0.461%

    No Known Activations