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

    Neuronpedia

    INDEX
    Explanations

    Rape, abuse, or RAINN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    룡
    0.41
    னி
    0.41
     रिश्ते
    0.40
    जबकि
    0.40
    ㄷ
    0.39
    讵
    0.38
     Kön
    0.38
    лося
    0.38
     स्पीड
    0.38
    TypeScript
    0.37
    POSITIVE LOGITS
     ra
    0.88
     Ra
    0.76
     RA
    0.74
    Ra
    0.70
     ра
    0.67
     RAP
    0.63
     Raiders
    0.62
     Raid
    0.61
    RA
    0.60
    ra
    0.59
    Act Density 0.044%

    No Known Activations