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

    Neuronpedia

    INDEX
    Explanations

    private

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ześ
    0.66
     નિર્
    0.65
    ಡಿ
    0.64
     যানবাহন
    0.60
    ികള
    0.59
    නා
    0.58
     Ingersoll
    0.58
    杯
    0.58
    ulang
    0.57
    वर्स
    0.57
    POSITIVE LOGITS
     private
    5.72
    Private
    5.25
    private
    5.24
     Private
    5.18
     PRIVATE
    4.74
    PRIVATE
    4.39
     privado
    4.37
     privato
    4.37
     privata
    4.31
    私
    4.24
    Act Density 0.400%

    No Known Activations