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

    Neuronpedia

    INDEX
    Explanations

    occurrences of non-text elements or symbols in structured data

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

    Code comments or headers

    np_acts-logits-general · gemini-2.0-flash

    decorative separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illustrazione
    -0.39
     --}}
    -0.39
     Neuk
    -0.38
     Vögel
    -0.37
    IsContent
    -0.35
    UrlResolution
    -0.35
    ANTLR
    -0.35
    ONAUT
    -0.34
     operazioni
    -0.34
    tran
    -0.34
    POSITIVE LOGITS
    endpush
    0.58
     nonUne
    0.57
     tartalomajánló
    0.49
    styleType
    0.47
     NSCoder
    0.47
    WithMany
    0.46
    UserScript
    0.45
    TRAILING
    0.43
     ſta
    0.43
    ponses
    0.42
    Act Density 1.248%

    No Known Activations