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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific numerical values or measurements

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

    number followed by punctuation or operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RequestMethod
    -0.53
    RunWith
    -0.47
     Krieger
    -0.47
     Herrmann
    -0.46
     Connors
    -0.45
     autorytatywna
    -0.44
     Horv
    -0.44
    jsonwebtoken
    -0.44
    Халык
    -0.44
     दर्ज
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.62
    DotNetBar
    0.55
     '\\;'
    0.54
     purpoſe
    0.53
     ſhall
    0.52
    sizeCache
    0.52
     Taille
    0.52
     sate
    0.52
     Slate
    0.50
    UnusedPrivate
    0.50
    Act Density 0.041%

    No Known Activations