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

    Neuronpedia

    INDEX
    Explanations

    periods and their frequency in the text

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

    numbered lists or academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.69
     ddelweddau
    -0.65
     initComponents
    -0.64
    новништво
    -0.59
     ſind
    -0.59
     beginnetje
    -0.57
    fromnode
    -0.56
     Italijanski
    -0.56
     CascadeType
    -0.56
    parsedMessage
    -0.56
    POSITIVE LOGITS
    medades
    0.39
    віть
    0.39
    同様に
    0.37
     remember
    0.35
     Les
    0.35
     houden
    0.34
     The
    0.34
     Orten
    0.34
     Marsden
    0.33
     times
    0.33
    Act Density 0.089%

    No Known Activations