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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getLocal
    -0.07
     Raz
    -0.07
     FileReader
    -0.07
     Ferr
    -0.06
     getBy
    -0.06
     SMTP
    -0.06
     Whatever
    -0.06
    ebe
    -0.06
     marginLeft
    -0.06
    \CMS
    -0.06
    POSITIVE LOGITS
     roses
    0.07
    (test
    0.07
    LB
    0.07
    _public
    0.06
     passwd
    0.06
    ูแล
    0.06
    losing
    0.06
     hesitate
    0.06
    _err
    0.06
     değ
    0.06
    Act Density 0.030%

    No Known Activations