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

    Neuronpedia

    INDEX
    Explanations

    disrespect and desecration of sacred/taboo subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.88
    at
    0.83
    in
    0.76
     shortcomings
    0.70
    is
    0.69
    ار
    0.68
    or
    0.67
    ut
    0.67
     debts
    0.65
     scont
    0.65
    POSITIVE LOGITS
     irrever
    0.77
    靼
    0.77
     Música
    0.73
    稩
    0.71
     größer
    0.71
    㐬
    0.70
    ক্রমে
    0.68
     Mặt
    0.68
     cenário
    0.67
    鬏
    0.67
    Act Density 0.010%

    No Known Activations