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

    Neuronpedia

    INDEX
    Explanations

    references to automated testing or programming conventions

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

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.61
    tagHelperRunner
    -0.60
     kaarangay
    -0.56
     ErrIntOverflow
    -0.48
     transfieras
    -0.48
    styleType
    -0.47
    exitRule
    -0.46
    rungsseite
    -0.45
    -------
    -0.44
     ModelRenderer
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.45
    capace
    0.41
     mógł
    0.40
    indelijk
    0.39
     dlatego
    0.37
     ersetzen
    0.37
     parezca
    0.37
     potrebbero
    0.36
    beelden
    0.36
     feed
    0.36
    Act Density 0.090%

    No Known Activations