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

    Neuronpedia

    INDEX
    Explanations

    points in code or text with version numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.99
     дописавши
    -0.84
     disambiguazione
    -0.81
     pinulongan
    -0.79
    seamnă
    -0.77
     ModelExpression
    -0.76
     تضيفلها
    -0.71
    AnchorTagHelper
    -0.69
    oredCriteria
    -0.67
    encodeWith
    -0.67
    POSITIVE LOGITS
     critic
    0.51
     Revised
    0.50
    Revised
    0.49
     fles
    0.46
    round
    0.46
     rev
    0.45
     الأس
    0.45
    Corrected
    0.44
     Ehe
    0.43
     crítica
    0.43
    Act Density 1.533%

    No Known Activations