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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aaa
    -0.08
     Iraqi
    -0.07
    _chunk
    -0.07
    หร
    -0.07
    ("(%
    -0.06
    ¯
    -0.06
     같
    -0.06
     Bec
    -0.06
    _season
    -0.06
     weren
    -0.06
    POSITIVE LOGITS
     τρα
    0.07
     imz
    0.06
    wing
    0.06
    _maximum
    0.06
    。「
    0.06
    .ModelSerializer
    0.06
     warned
    0.06
     vamp
    0.06
     �
    0.06
     phận
    0.06
    Act Density 0.072%

    No Known Activations