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

    Neuronpedia

    INDEX
    Explanations

    Fine dining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.47
    V
    1.45
    Т
    1.40
    K
    1.34
    T
    1.34
    ב
    1.34
    िंग
    1.32
    N
    1.29
    ने
    1.28
    S
    1.28
    POSITIVE LOGITS
    k
    1.23
    ك
    1.15
    يقة
    1.12
    z
    1.02
    仩
    1.00
     Павел
    0.96
    <0xBB>
    0.91
    ки
    0.91
    <0x99>
    0.90
    elijke
    0.90
    Act Density 0.004%

    No Known Activations