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

    Neuronpedia

    INDEX
    Explanations

    it looks for source code

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.75
     Италијани
    -0.75
    IsContent
    -0.70
    MLLoader
    -0.68
    adaptiveStyles
    -0.67
    NameInMap
    -0.65
    orteur
    -0.63
    parsedMessage
    -0.63
    anyard
    -0.63
     tartalomajánló
    -0.63
    POSITIVE LOGITS
     المث
    0.53
     Bla
    0.53
    itespace
    0.52
     Spar
    0.51
     White
    0.49
    iseta
    0.47
    isburg
    0.47
     English
    0.47
     many
    0.47
     no
    0.46
    Act Density 1.600%

    No Known Activations