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

    Neuronpedia

    INDEX
    Explanations

    swear words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🥲
    0.63
    Good
    0.62
     Good
    0.62
    ོ
    0.62
    ㅠ
    0.61
    ㅜ
    0.60
     bons
    0.58
    ufig
    0.57
     sighed
    0.57
    वय
    0.56
    POSITIVE LOGITS
    telek
    0.73
     సినిమాలు
    0.72
     Fiction
    0.70
     Titles
    0.69
     TMC
    0.67
    ától
    0.67
    FNO
    0.67
     marinade
    0.67
    seat
    0.66
    gF
    0.66
    Act Density 0.021%

    No Known Activations