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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bump
    -0.06
    [Math
    -0.06
     tbl
    -0.06
     Wash
    -0.06
     AccessToken
    -0.06
     Gan
    -0.06
    aturdays
    -0.06
     Kanye
    -0.06
     Actors
    -0.06
     Bloss
    -0.05
    POSITIVE LOGITS
    ::__
    0.07
     regarded
    0.06
    acha
    0.06
    $sql
    0.06
    ')}}">
    0.06
    より
    0.06
     Vertical
    0.06
    regon
    0.06
    subplot
    0.06
     prés
    0.06
    Act Density 0.015%

    No Known Activations