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

    Neuronpedia

    INDEX
    Explanations

    real-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acterísticas
    0.45
    পূর্ন
    0.42
     severally
    0.42
     আক্রমন
    0.42
    াড়া
    0.41
    股份
    0.41
    ष्क
    0.41
    )^{[\
    0.40
    ೇ
    0.40
     estremamente
    0.39
    POSITIVE LOGITS
     real
    1.38
    Real
    1.19
     Real
    1.08
    real
    1.07
     реа
    1.05
     REAL
    1.04
    REAL
    0.98
     रियल
    0.97
     reale
    0.89
     reales
    0.87
    Act Density 0.031%

    No Known Activations