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

    Neuronpedia

    INDEX
    Explanations

    references to notable authors and their contributions to literature or society

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

    Follows "like"

    np_acts-logits-general · gemini-2.0-flash

    like comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     как
    -0.64
     as
    -0.61
     even
    -0.57
     como
    -0.56
     addirittura
    -0.55
    even
    -0.54
    EVEN
    -0.52
     як
    -0.50
     EVEN
    -0.50
    Even
    -0.49
    POSITIVE LOGITS
     Paglinawan
    0.94
    一样
    0.87
    脚注の使い方
    0.85
     незавершена
    0.84
    IVEREF
    0.79
     vậy
    0.78
     did
    0.74
     CURIAM
    0.72
    那样
    0.72
    ValueStyle
    0.71
    Act Density 0.318%

    No Known Activations