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

    Neuronpedia

    INDEX
    Explanations

    display rules and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जांच
    0.41
     shitty
    0.41
    ड़ियां
    0.39
    걔
    0.38
     Kemudian
    0.38
    rennt
    0.38
     coursework
    0.38
     الدراسي
    0.38
     해주
    0.37
    긴
    0.37
    POSITIVE LOGITS
    ius
    0.37
     π
    0.37
    Ix
    0.37
     fo
    0.35
     vi
    0.34
     modern
    0.34
    [
    0.34
    ㎖
    0.34
    on
    0.34
     mammalian
    0.34
    Act Density 0.003%

    No Known Activations