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

    Neuronpedia

    INDEX
    Explanations

    words with diacritics or special characters

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

    references to specific mathematical symbols or notations

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

    special characters and foreign letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.71
    Попис
    -0.62
    WriteAttribute
    -0.58
     Públicas
    -0.58
    Демографія
    -0.57
     PeEnEo
    -0.56
    Datuak
    -0.55
    VideoCapture
    -0.53
    @@@@@@@@
    -0.50
    ByDefault
    -0.49
    POSITIVE LOGITS
    oco
    0.55
    üdis
    0.53
    ü
    0.52
    tsburgh
    0.52
    viewDidLoad
    0.50
    ⎩
    0.50
    JUnit
    0.50
    러나
    0.49
    iconductor
    0.49
    高く
    0.49
    Act Density 0.094%

    No Known Activations