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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references in academic citations

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

    digits followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sem
    -0.42
     vVar
    -0.42
    =="")
    -0.40
     McDonough
    -0.40
     Lightboxes
    -0.40
    ]--;
    -0.39
     Cummings
    -0.38
    횟
    -0.38
    ':{'
    -0.36
    ंदीखरीदारी
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.51
     transférez
    0.50
    OOTDTY
    0.49
    MessageTagHelper
    0.49
     GenerationType
    0.49
     forState
    0.49
    saraba
    0.48
     للمعارف
    0.47
     PropTypes
    0.46
     publiek
    0.46
    Act Density 0.022%

    No Known Activations