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

    Neuronpedia

    INDEX
    Explanations

    censorship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     irritate
    0.39
    ދު
    0.39
    правля
    0.37
     вечер
    0.36
    电源
    0.36
     সম্র
    0.35
     entferne
    0.35
    шибка
    0.34
    學院
    0.34
    Нау
    0.34
    POSITIVE LOGITS
     cens
    0.78
     Cens
    0.70
     censor
    0.62
    cens
    0.58
     censorship
    0.55
     censored
    0.50
     CEN
    0.47
     censure
    0.46
     цен
    0.44
    cene
    0.44
    Act Density 0.000%

    No Known Activations