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

    Neuronpedia

    INDEX
    Explanations

    elements indicating structured programming methods or functions

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

    Code or syntax-related tokens

    np_acts-logits-general · gemini-2.0-flash

    exert influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.69
    IVEREF
    -0.62
    Personensuche
    -0.56
    bootstrapcdn
    -0.54
    principalColumn
    -0.52
     transférez
    -0.50
    өз
    -0.50
    انجليز
    -0.50
    ţei
    -0.49
     Soit
    -0.49
    POSITIVE LOGITS
     */
    0.50
     שוליים
    0.49
     trajets
    0.49
     désolés
    0.49
    postcss
    0.48
    phylo
    0.47
     يتيمه
    0.46
    EndInit
    0.46
    OTING
    0.45
    addCriterion
    0.45
    Act Density 0.023%

    No Known Activations