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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters within programming or mathematical expressions

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

    'O' followed by math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.58
    fitrión
    -0.48
    namic
    -0.46
     sterk
    -0.45
     Lank
    -0.45
     Strong
    -0.45
    estries
    -0.45
    termilk
    -0.44
    исленность
    -0.44
     surla
    -0.44
    POSITIVE LOGITS
     O
    0.73
    O
    0.72
     OI
    0.57
    OQ
    0.54
     ओ
    0.53
     OO
    0.50
     Oll
    0.50
     Oden
    0.50
     Ogle
    0.50
     Oo
    0.49
    Act Density 0.135%

    No Known Activations