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

    Neuronpedia

    INDEX
    Explanations

    brush

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.79
    IntoConstraints
    -0.73
    DockStyle
    -0.71
     ProtoMessage
    -0.68
    XmlAccessorType
    -0.68
     cherchés
    -0.66
    GOTREF
    -0.63
     useDispatch
    -0.61
    InstrumentedTest
    -0.60
    HostException
    -0.59
    POSITIVE LOGITS
     up
    0.53
     shoulders
    0.45
     quoti
    0.44
     aside
    0.44
    RESH
    0.42
     Shoulders
    0.42
    aside
    0.42
     Minor
    0.41
     minor
    0.41
    )))),
    0.41
    Act Density 0.002%

    No Known Activations