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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Routed
    0.40
     bào
    0.40
    원을
    0.38
    ຫ
    0.37
    RANGER
    0.37
    バシー
    0.37
     Ekonomi
    0.36
    یکیشن
    0.36
     эко
    0.35
    หน
    0.35
    POSITIVE LOGITS
    Guild
    0.42
     Gun
    0.40
     çeşitli
    0.37
     Saul
    0.37
    GPU
    0.37
     gus
    0.37
     gauze
    0.37
     جيم
    0.36
    gust
    0.36
    gpu
    0.36
    Act Density 0.020%

    No Known Activations