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

    Neuronpedia

    INDEX
    Explanations

    end punctuation marks and sentence terminators

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

    end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.77
    OGND
    -0.65
    Diweddarwch
    -0.61
    PreferredItem
    -0.55
    RegressionTest
    -0.52
    TypedDataSet
    -0.50
    FieldNumber
    -0.48
    TagMode
    -0.48
     Photocase
    -0.47
    ніципалі
    -0.47
    POSITIVE LOGITS
     kapturem
    0.40
     båda
    0.39
    RectangleBorder
    0.38
     keduanya
    0.38
    IntoConstraints
    0.38
    Personensuche
    0.37
     seksual
    0.35
     KeyError
    0.35
     ValueError
    0.35
     begge
    0.34
    Act Density 0.133%

    No Known Activations