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

    Neuronpedia

    INDEX
    Explanations

    convincing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     misogyn
    -0.07
    рива
    -0.07
    .finish
    -0.06
    めた
    -0.06
    udur
    -0.06
     огра
    -0.06
     Од
    -0.06
     deb
    -0.06
     idea
    -0.06
    .Char
    -0.06
    POSITIVE LOGITS
     Vinyl
    0.07
     uniformly
    0.07
    (ed
    0.06
     أمريكي
    0.06
    疆
    0.06
    (rgb
    0.06
    اوه
    0.06
    _APPS
    0.06
    LARI
    0.06
     اساس
    0.06
    Act Density 0.001%

    No Known Activations