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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure elements

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

    json, List, array types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.84
     للاسماء
    -0.66
    #+#
    -0.64
    AddTagHelper
    -0.63
    expandindo
    -0.62
    Personensuche
    -0.61
    bootstrapcdn
    -0.60
     Numerade
    -0.59
     tartalomajánló
    -0.59
     الحره
    -0.59
    POSITIVE LOGITS
     múltiple
    0.45
     člán
    0.42
     []*
    0.42
     zachod
    0.38
    Varios
    0.36
    들이
    0.35
     varios
    0.35
     varias
    0.35
     články
    0.35
    varargin
    0.34
    Act Density 0.108%

    No Known Activations