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

    Neuronpedia

    INDEX
    Explanations

    language from scientific experiments

    oai_token-act-pair · gemini-2.0-flash

    experiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enderror
    -0.56
    EndGlobalSection
    -0.47
    ClCompile
    -0.46
    enterOuterAlt
    -0.45
    #
    -0.44
    cresc
    -0.44
    väll
    -0.44
    devtools
    -0.43
    рио
    -0.43
     ensa
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.80
    IntoConstraints
    0.60
    ніципалі
    0.60
    unger
    0.57
    ัติ
    0.56
    Lycka
    0.54
    TypedDataSet
    0.52
    CDCl
    0.50
     oldValue
    0.50
    IndentedString
    0.50
    Act Density 6.147%

    No Known Activations