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

    Neuronpedia

    INDEX
    Explanations

    contradiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.96
    theless
    -0.87
    RegressionTest
    -0.85
    __":
    -0.85
    IsMutable
    -0.84
    WriteTagHelper
    -0.83
    itudinal
    -0.82
    styleType
    -0.81
    queryInterface
    -0.79
    Hozzáférés
    -0.79
    POSITIVE LOGITS
    e
    0.54
    f
    0.52
    a
    0.52
    de
    0.51
    en
    0.51
    d
    0.49
    or
    0.48
    on
    0.48
    l
    0.47
    ron
    0.47
    Act Density 0.061%

    No Known Activations