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

    Neuronpedia

    INDEX
    Explanations

    references to standards and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Standard" followed by "deviation" or "error"

    np_acts-logits-general · gemini-2.0-flash

    standard deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FFIC
    -0.67
    ModelSerializer
    -0.64
     AssemblyTitle
    -0.64
    RepeatedField
    -0.62
    tagHelperRunner
    -0.62
    xase
    -0.61
    utilisons
    -0.61
     onPostExecute
    -0.60
    gdx
    -0.60
    omitempty
    -0.59
    POSITIVE LOGITS
     deviation
    1.05
    isation
    1.03
    Deviation
    0.88
     Deviation
    0.87
     deviations
    0.82
     bearer
    0.81
     bearers
    0.80
    StandardCharsets
    0.78
    deviation
    0.77
    ising
    0.75
    Act Density 0.094%

    No Known Activations