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

    Neuronpedia

    INDEX
    Explanations

    identifiers and their definitions in code representations

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

    return null if/false if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.45
     nakalista
    -0.44
    Morfologia
    -0.43
     المعيارى
    -0.43
    -0.42
    Билгалдахарш
    -0.41
    béco
    -0.40
    Datuak
    -0.40
    borne
    -0.40
    ghold
    -0.39
    POSITIVE LOGITS
    ="@+
    0.46
     propOrder
    0.42
     objs
    0.40
     HasFactory
    0.40
     flu
    0.38
    FromNib
    0.38
     meg
    0.37
    تقاوى
    0.37
    chyma
    0.36
     mus
    0.36
    Act Density 0.122%

    No Known Activations