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

    Neuronpedia

    INDEX
    Explanations

    censorship suppression of dissent and freedoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     завер
    0.76
    henius
    0.74
    ocommerce
    0.74
     قرارد
    0.74
    ர்ச்சி
    0.71
    פים
    0.71
    ூல்
    0.70
     adduct
    0.70
     primal
    0.69
    axial
    0.68
    POSITIVE LOGITS
     censorship
    2.35
     censored
    2.05
     Cens
    2.04
     censor
    2.03
     censoring
    1.98
     repressive
    1.72
     totalitarian
    1.70
     repression
    1.69
    cens
    1.69
     cens
    1.60
    Act Density 0.108%

    No Known Activations