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

    Neuronpedia

    INDEX
    Explanations

    abnormality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osomal
    -0.07
    gregar
    -0.07
     Worksheets
    -0.06
    _out
    -0.06
    ↵    
↵
    -0.06
     ж
    -0.06
    _dtype
    -0.06
     rootReducer
    -0.06
    (Program
    -0.06
    로
    -0.06
    POSITIVE LOGITS
     baths
    0.06
    stdint
    0.06
    Station
    0.06
     footh
    0.06
    exact
    0.06
     indicators
    0.06
     policies
    0.06
    čně
    0.06
    kek
    0.06
    ثل
    0.06
    Act Density 0.019%

    No Known Activations