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

    Neuronpedia

    INDEX
    Explanations

    principles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _indices
    -0.08
    破门
    -0.07
     selecion
    -0.07
     Tray
    -0.07
     İnt
    -0.07
    作者所有
    -0.07
     würde
    -0.07
     discuss
    -0.07
     turkey
    -0.07
    apellido
    -0.07
    POSITIVE LOGITS
    cams
    0.07
    섬
    0.07
    開放
    0.07
    一是
    0.07
    щит
    0.06
    יצ
    0.06
    (rawValue
    0.06
    .LookAndFeel
    0.06
     Bayer
    0.06
    IB
    0.06
    Act Density 0.001%

    No Known Activations