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

    Neuronpedia

    INDEX
    Explanations

    a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multicolor
    0.38
     berbentuk
    0.38
    乱
    0.37
     компью
    0.37
    内置
    0.37
    0.37
    宽
    0.36
    特征
    0.36
    织
    0.35
    tiles
    0.35
    POSITIVE LOGITS
     моги
    0.45
    漀
    0.40
     फिल
    0.39
     Burger
    0.37
     SUP
    0.37
     burger
    0.37
    Burger
    0.36
     অন্যত্র
    0.36
     SII
    0.36
    ುತ್ತಿರುವ
    0.35
    Act Density 0.051%

    No Known Activations