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
     Brushes
    -0.07
    Aware
    -0.07
     tariff
    -0.07
    เจร
    -0.07
    πτυ
    -0.07
    imony
    -0.06
    Scoped
    -0.06
    Năm
    -0.06
     disjoint
    -0.06
    InlineData
    -0.06
    POSITIVE LOGITS
    573
    0.06
    ACK
    0.06
     animated
    0.06
    Meet
    0.06
    (props
    0.06
            ↵↵
    0.05
     Dominion
    0.05
    535
    0.05
    Tom
    0.05
    _graphics
    0.05
    Act Density 0.032%

    No Known Activations