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

    Neuronpedia

    INDEX
    Explanations

    fingers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    2.30
    т
    1.91
    atl
    1.70
    क
    1.55
    ق
    1.52
     Диа
    1.47
    yout
    1.44
    ف
    1.42
    લ
    1.42
    ન
    1.40
    POSITIVE LOGITS
    ALITY
    2.09
     dakika
    1.98
     progenitor
    1.91
    ALK
    1.87
    ᆸ
    1.86
    Finger
    1.84
    ᆹ
    1.84
    骖
    1.82
    就像
    1.78
    缈
    1.78
    Act Density 0.006%

    No Known Activations