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

    Neuronpedia

    INDEX
    Explanations

    code/SQL queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dua
    -0.09
    ائز
    -0.07
    _order
    -0.07
    uat
    -0.06
    Mirror
    -0.06
     Composite
    -0.06
    acılık
    -0.06
     مفهوم
    -0.06
    Ctrls
    -0.06
     Citizens
    -0.06
    POSITIVE LOGITS
    ("--------------------------------
    0.06
    预
    0.06
    редел
    0.06
    /react
    0.06
    ุคคล
    0.06
     řešení
    0.06
    ().'/
    0.06
    ัพท
    0.06
    prevent
    0.06
     قانون
    0.06
    Act Density 0.024%

    No Known Activations