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

    Neuronpedia

    INDEX
    Explanations

    breach occurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actualizaciones
    0.58
    Ｓ
    0.56
     arbres
    0.54
     nieruchomości
    0.52
    ｓ
    0.51
    աբ
    0.50
    ر
    0.49
    ες
    0.48
    ﻵ
    0.48
    𝘀
    0.48
    POSITIVE LOGITS
     \
    0.47
     SUV
    0.46
     DUI
    0.44
     PVC
    0.44
     ROI
    0.43
     Luther
    0.42
     Mayo
    0.42
     soup
    0.41
     jersey
    0.41
     Soup
    0.41
    Act Density 0.000%

    No Known Activations