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

    Neuronpedia

    INDEX
    Explanations

    sequences of indentations or whitespace in code

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

    code and archaic spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.36
     bailarina
    -0.34
     Foundation
    -0.34
     saben
    -0.33
     exposición
    -0.33
     vengan
    -0.33
    -0.32
    -0.32
     يتيمه
    -0.32
    derung
    -0.32
    POSITIVE LOGITS
     NSCoder
    0.67
     للاسماء
    0.63
    ſelf
    0.63
     itſelf
    0.60
    richTextPanel
    0.58
    AddTagHelper
    0.57
    ſelves
    0.57
     iſt
    0.56
     greateſt
    0.55
    Personendaten
    0.54
    Act Density 0.021%

    No Known Activations