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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    821
    -0.06
     zel
    -0.06
    theless
    -0.06
    decl
    -0.06
    Often
    -0.06
     consolation
    -0.06
    ITO
    -0.06
     Shut
    -0.06
     tumors
    -0.06
    ?>
↵
↵
    -0.06
    POSITIVE LOGITS
    .evaluate
    0.07
    _bw
    0.06
    bundles
    0.06
     escort
    0.06
    ierce
    0.06
    .logs
    0.06
     arbe
    0.06
    ザー
    0.06
    .Promise
    0.06
     eriş
    0.06
    Act Density 0.003%

    No Known Activations