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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace and punctuation in text

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

    programmatic elements and chemical suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    исленность
    -0.43
    TProtocol
    -0.40
    IContainer
    -0.39
    İstinadlar
    -0.38
     informée
    -0.36
     Sm
    -0.36
     Wikimedijinoj
    -0.36
    たくない
    -0.34
    utilisons
    -0.34
    ркут
    -0.34
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.55
    +:+
    0.48
    rungsseite
    0.48
     FetchType
    0.47
     Vikipedi
    0.46
    transQ
    0.46
    Revenir
    0.44
     nakalista
    0.44
    EndContext
    0.44
    endpush
    0.43
    Act Density 0.146%

    No Known Activations