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

    Neuronpedia

    INDEX
    Explanations

    legal, factual, or activity descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">%
    1.26
     rãi
    1.10
    ski
    1.09
    ic
    1.09
    stein
    1.07
    esco
    1.05
     sàng
    1.05
     falo
    1.02
    icc
    1.02
    ıştır
    1.01
    POSITIVE LOGITS
    konom
    1.44
    പക്ഷം
    1.37
    तावनी
    1.30
    शय
    1.26
    邪魔
    1.26
    បត្តិ
    1.25
    pants
    1.24
     ナイス
    1.22
    ㄸ
    1.22
    僕
    1.21
    Act Density 0.000%

    No Known Activations