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

    Neuronpedia

    INDEX
    Explanations

    references to specific news sources or media outlets

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

    daily newspaper titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.79
    RectangleBorder
    -0.77
    Diweddarwch
    -0.71
     BorderSide
    -0.67
     '\\;'
    -0.66
    GEBURTSDATUM
    -0.65
    featureID
    -0.64
     Vikipedi
    -0.63
    transQ
    -0.60
    InputTagHelper
    -0.55
    POSITIVE LOGITS
    IllegalArgument
    0.40
    Smith
    0.38
    Loop
    0.35
    Derbyniad
    0.34
    setOutput
    0.33
     saling
    0.33
     Smith
    0.33
    GetValue
    0.32
    Pyx
    0.32
    Truthy
    0.32
    Act Density 0.025%

    No Known Activations