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

    Neuronpedia

    INDEX
    Explanations

    identifiers and data structures

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

    JSON and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.67
     للمعارف
    -0.66
     الرياضيه
    -0.61
     nonUne
    -0.57
     kasarigan
    -0.57
    Билгалдахарш
    -0.57
     Roskov
    -0.54
     snippetHide
    -0.52
    حوالہ
    -0.52
     nahilalakip
    -0.51
    POSITIVE LOGITS
    ​
    0.35
     råd
    0.33
     mérito
    0.32
     qualités
    0.31
     diriger
    0.31
     vektör
    0.31
     olup
    0.30
     InputDecoration
    0.30
     Recent
    0.30
     malzeme
    0.30
    Act Density 0.176%

    No Known Activations