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

    Neuronpedia

    INDEX
    Explanations

    e.g. or such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䐪
    0.48
    otra
    0.43
    まさに
    0.38
    ወት
    0.38
    ುದು
    0.37
    odus
    0.37
     اہلِ
    0.37
    wamy
    0.37
     দেখিয়
    0.37
    ᄆ
    0.36
    POSITIVE LOGITS
    比如
    2.28
     เช่น
    2.25
    例如
    2.11
    例えば
    2.11
    например
    2.06
     например
    2.02
     मसलन
    1.98
     Например
    1.94
    যেমন
    1.91
     poput
    1.91
    Act Density 0.378%

    No Known Activations