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

    Neuronpedia

    INDEX
    Explanations

    references to string and integer data types and their associated methods

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

    expressions that start with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.66
     @}
    -0.65
     queſta
    -0.63
    AddTagHelper
    -0.59
    BagConstraints
    -0.59
    !*\
    -0.59
    pantalones
    -0.57
    __":
    -0.56
    AccessorTable
    -0.55
    windowFixed
    -0.54
    POSITIVE LOGITS
     Wicidata
    0.35
     tomada
    0.34
    (
    0.32
     declaró
    0.30
     Vorles
    0.30
     îns
    0.29
     ordinaria
    0.29
     känd
    0.28
     Einwilligung
    0.28
     degrés
    0.27
    Act Density 0.008%

    No Known Activations