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

    Neuronpedia

    INDEX
    Explanations

    preventing or stopping actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.83
    де
    0.78
    при
    0.75
    einander
    0.74
    的不同
    0.70
    گی
    0.69
     different
    0.69
    ωσ
    0.69
     Different
    0.69
    מים
    0.68
    POSITIVE LOGITS
     altogether
    0.99
     catég
    0.91
     wszel
    0.84
     impide
    0.84
    tive
    0.83
    ishment
    0.80
    碍
    0.79
    ുവെ
    0.77
    wirkung
    0.77
    갑습니다
    0.76
    Act Density 0.274%

    No Known Activations