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

    Neuronpedia

    INDEX
    Explanations

    punctuation and speech-related expressions

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

    direct speech attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.64
    ContentAsync
    -0.53
    VIAF
    -0.52
    featureID
    -0.50
    TypedDataSet
    -0.49
    AccessorTable
    -0.49
     cref
    -0.49
    RegressionTest
    -0.47
     Wicidata
    -0.47
    Hauptartikel
    -0.46
    POSITIVE LOGITS
     volon
    0.36
    뀔
    0.35
    釁
    0.35
    깥
    0.35
     defence
    0.34
     fiscales
    0.34
     Trá
    0.33
    Consumer
    0.33
     gouverneur
    0.33
     HttpNotFound
    0.32
    Act Density 0.033%

    No Known Activations