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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structure definitions and properties

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

    code-related terms and structures in programming or software definitions

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

    code followed by terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '])){
    -1.03
    "],
    -0.96
    ++
    -0.88
    "];
    -0.88
    }]
    -0.87
    ']))
    -0.85
    '){
    -0.85
    '):
    -0.84
    ')){
    -0.84
    ')):
    -0.84
    POSITIVE LOGITS
    .
    0.52
    ANTLR
    0.48
     imitating
    0.47
     refleja
    0.45
     marcó
    0.45
     näin
    0.44
     realises
    0.42
    хьтан
    0.41
    Putting
    0.41
     tourmaline
    0.41
    Act Density 0.043%

    No Known Activations