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

    Neuronpedia

    INDEX
    Explanations

    as followed by comparison or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.00
    т
    1.91
    м
    1.82
    tay
    1.62
    k
    1.54
    tion
    1.52
    م
    1.50
    es
    1.49
    л
    1.48
    ים
    1.45
    POSITIVE LOGITS
    sembles
    1.83
    inine
    1.61
    ymmet
    1.59
    cribable
    1.29
    ignment
    1.27
     וכ
    1.27
     минимум
    1.16
     물론
    1.15
    的情況
    1.13
    いたり
    1.13
    Act Density 0.753%

    No Known Activations