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

    Neuronpedia

    INDEX
    Explanations

    lewd acts in ponds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಿಕ್
    -0.08
    전체
    -0.08
    、市
    -0.08
    、生
    -0.08
     отличие
    -0.08
    ーズ
    -0.08
    _UNUSED
    -0.08
     информа
    -0.08
    ندر
    -0.07
     основу
    -0.07
    POSITIVE LOGITS
    filename
    0.08
    caption
    0.08
    quote
    0.08
    forecast
    0.08
     threshold
    0.08
     shampoo
    0.07
    tweet
    0.07
     thresh
    0.07
     teñ
    0.07
     Farn
    0.07
    Act Density 0.031%

    No Known Activations