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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ederek
    -0.06
    لى
    -0.06
    가는
    -0.06
    _Con
    -0.06
     nombres
    -0.06
    filtr
    -0.06
    적으로
    -0.06
     فلس
    -0.06
     LogManager
    -0.06
     Glory
    -0.06
    POSITIVE LOGITS
    iz
    0.07
     ویژه
    0.07
    nel
    0.06
     removeFromSuperview
    0.06
    Fine
    0.06
    ��
    0.06
     jaar
    0.06
     topped
    0.06
    IZ
    0.06
    ization
    0.06
    Act Density 0.000%

    No Known Activations