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

    Neuronpedia

    INDEX
    Explanations

    python code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivity
    0.41
    marble
    0.40
    ثله
    0.36
     والح
    0.35
    omega
    0.35
    粹
    0.35
    संधान
    0.34
    d
    0.33
    mede
    0.33
    サイクル
    0.33
    POSITIVE LOGITS
    ی
    0.42
    𝙚
    0.35
     Podium
    0.33
     consulte
    0.31
     scratched
    0.31
    𝙡
    0.31
    ご購入
    0.31
    িয়ে
    0.31
     berc
    0.31
    izontal
    0.31
    Act Density 0.918%

    No Known Activations