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

    Neuronpedia

    INDEX
    Explanations

    illegal activities or markets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ση
    0.54
    ತಿ
    0.53
    ή
    0.52
    blusa
    0.48
    ニュアル
    0.47
    ች
    0.46
    Если
    0.46
    ικό
    0.45
     Если
    0.45
     Marino
    0.45
    POSITIVE LOGITS
     illegal
    0.96
     Illegal
    0.82
    Illegal
    0.82
     ilegal
    0.82
     illicit
    0.80
     illegally
    0.77
    非法
    0.76
    illegal
    0.75
     अवैध
    0.75
     незакон
    0.74
    Act Density 0.053%

    No Known Activations