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

    Neuronpedia

    INDEX
    Explanations

    limits or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.56
     are
    0.45
     a
    0.44
    an
    0.43
    p
    0.41
    is
    0.41
    st
    0.40
     and
    0.39
    T
    0.39
    k
    0.39
    POSITIVE LOGITS
    于
    0.48
     galore
    0.47
    ୯
    0.45
    쳐
    0.43
     многи
    0.43
    了大
    0.43
     Bereichen
    0.42
     显示
    0.42
     остров
    0.42
     すぎ
    0.42
    Act Density 0.053%

    No Known Activations