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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ad
    -0.08
    om
    -0.08
     fluffy
    -0.06
    _dd
    -0.06
    gom
    -0.06
     Usage
    -0.06
     Him
    -0.06
     sea
    -0.06
     Com
    -0.06
    Category
    -0.06
    POSITIVE LOGITS
    KN
    0.07
    [property
    0.07
    """↵↵↵
    0.06
    [var
    0.06
    [selected
    0.06
    IBUTES
    0.06
     SEAL
    0.06
     Ö
    0.06
     церков
    0.06
    _pairs
    0.06
    Act Density 0.010%

    No Known Activations