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

    Neuronpedia

    INDEX
    Explanations

    code methods and properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _scalar
    -0.07
    acz
    -0.07
    fur
    -0.07
    IR
    -0.07
    718
    -0.07
    _VAL
    -0.07
     bound
    -0.07
    oidal
    -0.06
    IZE
    -0.06
    emi
    -0.06
    POSITIVE LOGITS
    重複重複
    0.06
     кв
    0.06
    /self
    0.06
    –and
    0.06
     additional
    0.06
     twitter
    0.06
     груз
    0.06
     华
    0.06
     jednodu
    0.06
    becue
    0.05
    Act Density 0.000%

    No Known Activations