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

    Neuronpedia

    INDEX
    Explanations

    structured elements in programming code that delineate blocks or sections

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

    json/javascript code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.38
    <eos>
    -0.30
    -0.25
    -0.22
     going
    -0.22
     marco
    -0.21
    -0.21
    -0.21
     warning
    -0.21
    -0.21
    POSITIVE LOGITS
     ujednoznacz
    0.98
    Personendaten
    0.95
     كومونز
    0.84
     HasFactory
    0.82
     kasarigan
    0.81
    styleType
    0.80
     surla
    0.78
     فريبيس
    0.78
    AndEndTag
    0.76
    sizeCache
    0.75
    Act Density 0.032%

    No Known Activations