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

    Neuronpedia

    INDEX
    Explanations

    Scientific figures/publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     You
    -0.07
    “One
    -0.06
     imageSize
    -0.06
    เด
    -0.06
     Guys
    -0.06
    Curve
    -0.06
    추
    -0.06
    )[
    -0.06
    ,</
    -0.06
     Dam
    -0.06
    POSITIVE LOGITS
    ์ต
    0.07
     dejtings
    0.07
     Burns
    0.07
    ิญญ
    0.06
    _RT
    0.06
     approximation
    0.06
    244
    0.06
    ячи
    0.06
    .mx
    0.06
    -proof
    0.06
    Act Density 0.000%

    No Known Activations