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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bitmap
    -0.07
     hentai
    -0.07
    蛊
    -0.07
     wurde
    -0.07
    antu
    -0.07
    updates
    -0.06
    cdf
    -0.06
    .Physics
    -0.06
    wordpress
    -0.06
    _SK
    -0.06
    POSITIVE LOGITS
     guarantees
    0.08
     coolest
    0.06
    $p
    0.06
    !=
    0.06
    ম
    0.06
     прием
    0.06
     ром
    0.06
    istan
    0.06
    aise
    0.06
    akest
    0.06
    Act Density 0.003%

    No Known Activations