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

    Neuronpedia

    INDEX
    Explanations

    Starts with introductory words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пр
    0.29
    ئیں۔
    0.28
    媑
    0.27
    apabb
    0.26
     معلوم
    0.26
    Dims
    0.26
     አይደ
    0.26
    ﾏ
    0.26
    㛺
    0.26
    》。
    0.25
    POSITIVE LOGITS
     cuyas
    0.31
     medals
    0.30
    ៨
    0.29
    ición
    0.29
     cuyos
    0.29
     cuya
    0.28
     devenu
    0.28
     których
    0.27
     чемпи
    0.27
     doppia
    0.27
    Act Density 0.000%

    No Known Activations