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

    Neuronpedia

    INDEX
    Explanations

    words used in discussions of technical problems or scheduled meetings

    oai_token-act-pair · gemini-2.0-flash

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.98
    TagMode
    -0.98
    rungsseite
    -0.95
     ModelExpression
    -0.93
     للاسماء
    -0.92
     насељу
    -0.90
    GraphicsUnit
    -0.85
     surla
    -0.84
    featureID
    -0.83
    RegressionTest
    -0.83
    POSITIVE LOGITS
     under
    2.77
    under
    2.38
    Under
    2.22
     Under
    2.20
     UNDER
    1.92
     bajo
    1.72
    UNDER
    1.70
     unter
    1.63
     sous
    1.51
     onder
    1.41
    Act Density 2.808%

    No Known Activations