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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [Boolean
    -0.06
     comentarios
    -0.06
     مشاركة
    -0.06
    _LOADING
    -0.06
     dinosaurs
    -0.06
     irresponsible
    -0.06
    ：<
    -0.06
     regulatory
    -0.06
    FileStream
    -0.05
     Tian
    -0.05
    POSITIVE LOGITS
     구
    0.07
     bankruptcy
    0.07
     时
    0.07
    ermann
    0.07
    ritos
    0.06
     stalk
    0.06
    (expr
    0.06
    ayed
    0.06
    ++↵
    0.06
    ///↵↵
    0.06
    Act Density 0.000%

    No Known Activations