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

    Neuronpedia

    INDEX
    Explanations

    Holocaust discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ίας
    0.80
    는
    0.78
    하는
    0.77
    unakan
    0.74
    ческих
    0.73
     انہ
    0.73
    εις
    0.71
    enças
    0.71
     prazo
    0.70
    ્ર
    0.69
    POSITIVE LOGITS
    ।
    0.95
    。
    0.93
    ara
    0.83
    }
    0.83
     Holocaust
    0.80
    '
    0.78
    א
    0.78
    。\
    0.77
     Fight
    0.74
     Tamaño
    0.72
    Act Density 0.002%

    No Known Activations