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

    Neuronpedia

    INDEX
    Explanations

    Justin Barrett, Portal Gateway, modal logic, Seth Ryan, Cate Blanchett

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    에
    2.47
    ो
    2.27
    কে
    2.23
    に
    2.03
    О
    1.95
    ُ
    1.93
    مان
    1.90
    ной
    1.87
    ੀ
    1.82
    مة
    1.79
    POSITIVE LOGITS
    corruption
    1.67
    xanth
    1.66
    missions
    1.65
    al
    1.61
    ج
    1.59
    ve
    1.58
    jumlah
    1.56
     Barcelone
    1.54
    t
    1.52
    bright
    1.48
    Act Density 0.091%

    No Known Activations