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

    Neuronpedia

    INDEX
    Explanations

    a range of words that appear to be related to academic research and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    Base, basis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.60
     חיצוניים
    -0.60
    OwnProperty
    -0.60
     NSCoder
    -0.58
    featureID
    -0.54
     đương
    -0.52
     kasarigan
    -0.52
     TextAppearance
    -0.52
     inflater
    -0.49
    migrationBuilder
    -0.49
    POSITIVE LOGITS
     base
    2.03
     bases
    1.70
    base
    1.69
     basis
    1.68
     Base
    1.61
    basis
    1.51
     baseline
    1.49
    Base
    1.49
     foundation
    1.48
     Basis
    1.45
    Act Density 3.976%

    No Known Activations