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

    Neuronpedia

    INDEX
    Explanations

    words related to requesting assistance and tasks for school or work

    oai_token-act-pair · gemini-2.0-flash

    Webpage or code text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.71
    tonsoft
    -0.66
     propOrder
    -0.65
    DoubleQuotes
    -0.65
    Unique
    -0.61
     Bellas
    -0.59
    Diwedd
    -0.58
    TypedDataSet
    -0.57
     Unique
    -0.56
     Exacts
    -0.56
    POSITIVE LOGITS
    redge
    0.49
     hins
    0.48
    ikian
    0.48
    ાં
    0.47
    SourceChecksum
    0.47
    ettu
    0.46
    hending
    0.46
     look
    0.45
    tamentos
    0.44
    look
    0.44
    Act Density 1.370%

    No Known Activations