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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    させて頂きます
    -0.93
    瀝
    -0.84
    Transkript
    -0.79
    krish
    -0.79
    étro
    -0.78
    hộp
    -0.77
    ようです
    -0.77
    scarlet
    -0.77
    kenzo
    -0.76
     cực
    -0.76
    POSITIVE LOGITS
     ול
    1.34
     ולה
    1.19
    ш
    0.94
    圧
    0.90
    ляции
    0.90
     بودند
    0.89
    Λ
    0.89
     Uy
    0.88
    MAL
    0.86
    Ά
    0.85
    Act Density 0.125%

    No Known Activations