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

    Neuronpedia

    INDEX
    Explanations

    variable values used in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.95
    ArrowToggle
    -0.87
     للمعارف
    -0.85
    GEBURTSDATUM
    -0.85
     متعلقه
    -0.83
    ніципалі
    -0.82
     kasarigan
    -0.77
    aarrggbb
    -0.75
     disambiguazione
    -0.75
     חיצוניים
    -0.73
    POSITIVE LOGITS
    Javadoc
    0.59
    sig
    0.48
    ted
    0.45
    (||
    0.45
    ,
    0.44
    ire
    0.43
     base
    0.43
    rap
    0.42
    INCREF
    0.42
    inh
    0.42
    Act Density 0.080%

    No Known Activations