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

    Neuronpedia

    INDEX
    Explanations

    commas and punctuation in natural language text

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    openqa
    -0.54
     emerged
    -0.51
     implying
    -0.50
    anguard
    -0.48
    tiste
    -0.48
    ēju
    -0.47
    стро
    -0.47
     macchina
    -0.47
     المنا
    -0.47
    onomy
    -0.47
    POSITIVE LOGITS
    EndGlobalSection
    0.88
    featureID
    0.73
    QMetaType
    0.71
    principalTable
    0.69
    RegistryLite
    0.69
    XmlType
    0.67
    Tembelea
    0.66
    DeleteBehavior
    0.66
     &___
    0.65
    EndContext
    0.64
    Act Density 1.298%

    No Known Activations