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

    Neuronpedia

    INDEX
    Explanations

    sections of the text containing significant events or conclusions

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

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cul
    -0.40
     Aro
    -0.40
    cul
    -0.40
     local
    -0.39
     Local
    -0.39
     bra
    -0.39
     Wal
    -0.38
    getC
    -0.38
     Фе
    -0.38
     Spark
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.88
     pinulongan
    0.77
     kasarigan
    0.70
    optionalTypeArgs
    0.67
    Erreferentziak
    0.67
    BufferException
    0.65
    MessageOf
    0.64
     betweenstory
    0.63
    ########.
    0.63
    enderror
    0.60
    Act Density 0.057%

    No Known Activations