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

    Neuronpedia

    INDEX
    Explanations

    programming and syntax-related constructs

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

    code syntax, punctuation, and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )}+\
    -0.36
    ISODE
    -0.36
     subsequently
    -0.34
     shot
    -0.34
     fü
    -0.33
    ToScroll
    -0.33
     alcanzado
    -0.32
    Reaching
    -0.32
     CGRect
    -0.32
    .'"
    -0.32
    POSITIVE LOGITS
    OGND
    0.67
    featureID
    0.62
    localctx
    0.62
    Derbyniad
    0.60
     Chwiliwch
    0.58
     kasarigan
    0.56
    fjspx
    0.55
     autorytatywna
    0.50
     $_"
    0.50
     miniaturka
    0.50
    Act Density 0.021%

    No Known Activations