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

    Neuronpedia

    INDEX
    Explanations

    content related to mathematical expressions or notation

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

    closing delimiters for code or math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    holdet
    -0.39
     eğer
    -0.36
     dévelo
    -0.36
     permiso
    -0.36
     judiciaire
    -0.35
     démocr
    -0.34
     constitucional
    -0.34
     destinées
    -0.34
     enseñanza
    -0.34
     légal
    -0.33
    POSITIVE LOGITS
    ]{
    0.90
     محفوظة
    0.80
    twimg
    0.76
    
    0.76
    endpush
    0.73
     snippetHide
    0.69
    CppMethod
    0.67
    __(/*!
    0.67
    ⟬
    0.65
    endregion
    0.65
    Act Density 0.006%

    No Known Activations