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

    Neuronpedia

    INDEX
    Explanations

    references to things that can be listed, reviewed, rated or criticized, especially on the internet

    oai_token-act-pair · gemini-2.0-flash

    diverse content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interesar
    -0.73
    性和
    -0.73
    rawDesc
    -0.69
     etc
    -0.69
    TProtocol
    -0.68
    Controllo
    -0.68
    مقاله
    -0.68
    ?,?,
    -0.67
    mogat
    -0.67
    TagMode
    -0.66
    POSITIVE LOGITS
     NSCoder
    0.40
    EDEFAULT
    0.34
     صوتيه
    0.32
    shadowRadius
    0.27
    kwds
    0.26
     ProtoMessage
    0.25
     uſe
    0.23
    exitRule
    0.22
     €)
    0.22
     an
    0.21
    Act Density 30.466%

    No Known Activations