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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Preceding capitalized words or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    San new BLM Q revision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naselje
    -0.54
    으면
    -0.52
    љено
    -0.50
    limsy
    -0.50
    stres
    -0.49
    Vidite
    -0.49
    ->___
    -0.49
     ten
    -0.48
    elang
    -0.48
    mları
    -0.48
    POSITIVE LOGITS
    enumi
    1.05
    enumii
    0.72
    存于互联网档案馆
    0.70
    istoitu
    0.69
    URLException
    0.69
     rowspan
    0.68
     مشين
    0.66
     handker
    0.63
    ImageContext
    0.61
     anhyd
    0.60
    Act Density 0.009%

    No Known Activations