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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptions of performance or ability in various contexts

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

    performance descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veiligheid
    -0.37
     digitais
    -0.32
    akaian
    -0.31
     republic
    -0.30
     inalámb
    -0.29
     standaard
    -0.29
    følge
    -0.29
     '[
    -0.29
     quæ
    -0.29
     خی
    -0.29
    POSITIVE LOGITS
    цездатний
    0.78
     ब्रेकडाउन
    0.68
     kasarigan
    0.65
    InjectAttribute
    0.62
    PropertyChanging
    0.60
    ⓧ
    0.57
     BoxFit
    0.57
     intStringLen
    0.56
    aarrggbb
    0.56
    ьаж
    0.56
    Act Density 0.014%

    No Known Activations