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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and symbols often used in programming or markup languages

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

    citation references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.88
     ModelExpression
    -0.57
    AddTagHelper
    -0.57
    DockStyle
    -0.55
    -0.54
     الرياضيه
    -0.54
    LookAnd
    -0.51
     '\\;'
    -0.49
    archiviato
    -0.47
    ConstraintMaker
    -0.47
    POSITIVE LOGITS
    __(/*!
    0.56
    CodeAttribute
    0.52
    íncia
    0.44
    AfterClass
    0.41
     Western
    0.41
     opérés
    0.40
    SuppressMessage
    0.40
     wester
    0.40
    CrossOrigin
    0.38
    hasMany
    0.38
    Act Density 0.007%

    No Known Activations