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

    Neuronpedia

    INDEX
    Explanations

    effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.77
     economy
    -0.73
     Economy
    -0.68
    economy
    -0.66
    Economy
    -0.66
     ECONOMY
    -0.64
    Hochspringen
    -0.63
    TestTools
    -0.63
     CreateTagHelper
    -0.61
     useDispatch
    -0.60
    POSITIVE LOGITS
     the
    0.79
     Main
    0.49
     developed
    0.47
    Main
    0.46
    transQ
    0.44
    出版年
    0.43
    Pozri
    0.42
    developed
    0.42
     insegn
    0.41
     perak
    0.41
    Act Density 0.000%

    No Known Activations