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

    Neuronpedia

    INDEX
    Explanations

    tied to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    1.20
    ០
    0.94
    ский
    0.89
    تي
    0.87
    يات
    0.86
    يز
    0.85
    ные
    0.84
    филлер
    0.84
    ۰
    0.82
    ших
    0.82
    POSITIVE LOGITS
    م
    1.21
    ’
    0.93
     a
    0.88
    ↵
    0.86
    بی
    0.86
    อ
    0.84
    पी
    0.82
     tied
    0.82
    จะ
    0.80
    आर
    0.80
    Act Density 0.043%

    No Known Activations