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

    Neuronpedia

    INDEX
    Explanations

    references to the presence or absence of specific conditions or entities in a dataset

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

    Follows nouns indicating existence or observation

    np_acts-logits-general · gemini-2.0-flash

    presence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zwald
    -0.42
    󠁢
    -0.42
    static
    -0.39
     Dunkel
    -0.38
     newOwner
    -0.38
    hoeddwyd
    -0.38
    inetic
    -0.36
     gewe
    -0.35
     Вікіпе
    -0.35
    torre
    -0.35
    POSITIVE LOGITS
    elemField
    0.56
    migrationBuilder
    0.48
    started
    0.45
    RegressionTest
    0.45
    AnimationsModule
    0.43
    TagMode
    0.43
    Composable
    0.42
     finnas
    0.42
    ordonnées
    0.42
     started
    0.41
    Act Density 0.939%

    No Known Activations