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

    Neuronpedia

    INDEX
    Explanations

    foreign language indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lisa
    0.31
     brows
    0.29
     Math
    0.29
     Sch
    0.28
     This
    0.28
     Dame
    0.28
     Provided
    0.27
     Flan
    0.27
     Lal
    0.27
     they
    0.27
    POSITIVE LOGITS
    וש
    0.33
    russian
    0.33
     യു
    0.31
    俄
    0.31
    ிற்க
    0.31
     러시아
    0.31
    ोलिक
    0.31
    ロシア
    0.30
    mud
    0.30
     hujan
    0.30
    Act Density 0.000%

    No Known Activations