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
     developing
    -0.07
     screaming
    -0.06
    _planes
    -0.06
     tells
    -0.06
     sewage
    -0.06
    isting
    -0.06
    bserv
    -0.06
    кие
    -0.06
    NEL
    -0.06
     Laf
    -0.06
    POSITIVE LOGITS
     каче
    0.08
     nostro
    0.07
     […]↵↵
    0.07
     clearfix
    0.06
    giatan
    0.06
     Noir
    0.06
     Combo
    0.06
    _;
    0.06
    (Model
    0.06
    .ShowDialog
    0.06
    Act Density 0.059%

    No Known Activations