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

    Neuronpedia

    INDEX
    Explanations

    words that are frequently used when asking for or giving advice or explanations

    oai_token-act-pair · gemini-2.0-flash

    general

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дописавши
    -1.06
     AssemblyCulture
    -1.06
     ModelExpression
    -0.91
    rungsseite
    -0.90
     <=",
    -0.88
    TagMode
    -0.86
    цездатний
    -0.86
    DockStyle
    -0.85
    addCriterion
    -0.84
    UserScript
    -0.84
    POSITIVE LOGITS
     general
    2.06
    general
    1.76
     generic
    1.52
     GENERAL
    1.51
    General
    1.50
     General
    1.46
     général
    1.41
    GENERAL
    1.38
     generalized
    1.37
     generale
    1.36
    Act Density 2.621%

    No Known Activations