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

    Neuronpedia

    INDEX
    Explanations

    attributes and values with the names "value", "tag", "update", "style"

    oai_token-act-pair · gemini-2.0-flash

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     value
    -0.87
    value
    -0.82
     values
    -0.81
    Value
    -0.77
     Value
    -0.75
    values
    -0.71
     Values
    -0.71
     VALUE
    -0.69
    Values
    -0.68
    的值
    -0.61
    POSITIVE LOGITS
    PullParser
    0.71
    SequentialGroup
    0.71
    ConstraintMaker
    0.69
    makeConstraints
    0.66
    хіво
    0.65
    SizeMode
    0.63
    UserScript
    0.63
    DMETHOD
    0.62
     BoxFit
    0.62
    BuildContext
    0.62
    Act Density 19.755%

    No Known Activations