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

    Neuronpedia

    INDEX
    Explanations

    undefined or uncertain things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kullanarak
    0.59
    कायदा
    0.53
     обы
    0.49
     inmediatamente
    0.48
     सिंपल
    0.48
     başarılı
    0.48
     memudahkan
    0.47
     nhắc
    0.47
     memperhatikan
    0.45
     Hochzeit
    0.45
    POSITIVE LOGITS
     uncertain
    2.30
     uncertainty
    2.03
     uncertainties
    1.99
    uncertain
    1.95
     unknowns
    1.89
     unclear
    1.87
     Uncertain
    1.86
     unknown
    1.81
     unsure
    1.77
     Uncertainty
    1.73
    Act Density 1.507%

    No Known Activations