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

    Neuronpedia

    INDEX
    Explanations

    code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getRow
    -0.07
     Donne
    -0.07
     Universe
    -0.07
    where
    -0.07
    HERE
    -0.06
    aviour
    -0.06
     runes
    -0.06
     Everyone
    -0.06
     quận
    -0.06
    _where
    -0.06
    POSITIVE LOGITS
     mohou
    0.07
     bitwise
    0.06
     callback
    0.06
    _mux
    0.06
    _legacy
    0.06
     sexy
    0.06
    ائز
    0.06
     satisfaction
    0.06
    ↵    ↵
    0.06
     Predictor
    0.06
    Act Density 0.010%

    No Known Activations