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

    Neuronpedia

    INDEX
    Explanations

    legal and government bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Á
    0.29
    Green
    0.28
     beliau
    0.27
    Abraham
    0.26
     हरा
    0.26
     Green
    0.26
     Dough
    0.25
     Soybean
    0.25
     Beverage
    0.25
    PU
    0.24
    POSITIVE LOGITS
     루트
    0.34
     Schrö
    0.33
    utum
    0.33
     midwives
    0.32
     scandalous
    0.32
     조건
    0.31
    mDatas
    0.31
    輳
    0.31
     NSFW
    0.30
     recommand
    0.30
    Act Density 0.000%

    No Known Activations