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

    Neuronpedia

    INDEX
    Explanations

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Simple
    0.59
    ira
    0.59
    Standard
    0.57
    रीत
    0.57
     classics
    0.55
     near
    0.55
    Basic
    0.55
     presque
    0.55
     almost
    0.55
     smaller
    0.55
    POSITIVE LOGITS
     How
    2.15
     how
    2.14
     apakah
    2.03
     What
    1.94
     क्या
    1.93
    How
    1.93
     Apakah
    1.93
     是否
    1.92
     Why
    1.84
     why
    1.82
    Act Density 1.232%

    No Known Activations