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

    Neuronpedia

    INDEX
    Explanations

    code, references, variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    наче
    -0.07
    吾
    -0.07
    outlined
    -0.06
    論
    -0.06
    ッツ
    -0.06
    LESS
    -0.06
    _prev
    -0.06
    your
    -0.06
    ९
    -0.06
    ष
    -0.06
    POSITIVE LOGITS
     dashed
    0.07
     green
    0.07
    (fabs
    0.06
     Kardashian
    0.06
    .sap
    0.06
     Федера
    0.06
    stdafx
    0.06
    (angle
    0.06
    (IServiceCollection
    0.06
     curl
    0.06
    Act Density 0.035%

    No Known Activations