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

    Neuronpedia

    INDEX
    Explanations

    numeric dimensions and measurements

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

    units of length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orina
    -0.28
     cumplido
    -0.27
     verrez
    -0.24
    </strong>
    -0.24
    ’
    -0.23
     taraf
    -0.23
     confianza
    -0.23
     pledges
    -0.23
     might
    -0.22
     предпо
    -0.22
    POSITIVE LOGITS
     betweenstory
    0.85
     nahilalakip
    0.76
    InputBorder
    0.75
     '\\;'
    0.75
     Monfieur
    0.75
     propOrder
    0.73
     Majefty
    0.72
    ViewChild
    0.71
    <pad>
    0.71
    <unused16>
    0.71
    Act Density 0.025%

    No Known Activations