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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations or notation involving variables and operators

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

    divisor of m

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.68
    ########.
    -0.57
    RectangleBorder
    -0.52
    Diweddarwch
    -0.52
     дописавши
    -0.50
     esternos
    -0.50
    MENAFN
    -0.49
     otomatig
    -0.49
    bewerken
    -0.48
    下载附件
    -0.46
    POSITIVE LOGITS
    weightedMode
    0.59
    uxxxx
    0.56
    protetor
    0.54
     betweenstory
    0.53
    tênis
    0.50
    pulseira
    0.47
    brinco
    0.47
    valget
    0.43
    เค้า
    0.43
    protoimpl
    0.43
    Act Density 0.163%

    No Known Activations