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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Notes" and variations of it

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

    the word Notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.56
     brinquedo
    -0.51
     فريبيس
    -0.46
     unicórnio
    -0.45
     amortecedor
    -0.45
    ParallelGroup
    -0.44
    endcsname
    -0.44
     comércio
    -0.44
     clearColor
    -0.44
     brinquedos
    -0.43
    POSITIVE LOGITS
     Notes
    2.30
    Notes
    2.23
     notes
    2.20
     NOTES
    2.03
    notes
    2.03
    NOTES
    1.84
     notas
    1.33
     Notas
    1.30
    Notas
    1.17
    笔记
    1.09
    Act Density 0.007%

    No Known Activations