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

    Neuronpedia

    INDEX
    Explanations

    political events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zahl
    0.57
     оплаты
    0.53
     сх
    0.48
     DOS
    0.47
     Фор
    0.47
     >>
    0.46
     má
    0.46
     опла
    0.46
     RCMP
    0.46
     KPMG
    0.45
    POSITIVE LOGITS
    rican
    0.52
    moil
    0.47
    rées
    0.43
    rard
    0.42
    cipline
    0.40
    rile
    0.40
    libat
    0.40
    enial
    0.40
     laughter
    0.39
    necks
    0.39
    Act Density 0.006%

    No Known Activations