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

    Neuronpedia

    INDEX
    Explanations

    that depict explicit sexual acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     że
    0.48
     että
    0.48
     ότι
    0.45
    的是
    0.42
     bahwa
    0.41
     যে
    0.40
     že
    0.39
    ថា
    0.37
    ว่า
    0.36
     दट
    0.36
    POSITIVE LOGITS
     they
    0.60
    soever
    0.56
    elbe
    0.48
    ched
    0.46
     heißt
    0.45
    વો
    0.44
    mashtami
    0.44
     gehen
    0.43
     আছেন
    0.43
     옳은
    0.42
    Act Density 0.008%

    No Known Activations