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

    Neuronpedia

    INDEX
    Explanations

    terms related to keyboard input and data processing

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

    completeness and sufficient complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.66
     ModelExpression
    -0.60
     المعيارى
    -0.58
     HasFactory
    -0.55
    setVerticalGroup
    -0.54
     صوتيه
    -0.54
    BeginContext
    -0.52
    Бахар
    -0.52
     kasarigan
    -0.50
    optarg
    -0.50
    POSITIVE LOGITS
     folha
    0.44
     suficientes
    0.44
     expresa
    0.41
     användas
    0.40
     expresar
    0.40
     dukungan
    0.40
     terbatas
    0.39
     används
    0.38
     pomocy
    0.38
     możliwości
    0.38
    Act Density 0.295%

    No Known Activations