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

    Neuronpedia

    INDEX
    Explanations

    code segments or functions involving parentheses and argument lists

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

    code snippets and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.75
    Tembelea
    -0.75
     للاسماء
    -0.68
    RegressionTest
    -0.68
    AndroidJUnit
    -0.66
    majánló
    -0.65
     snippetHide
    -0.63
    ReusableCell
    -0.63
    principalColumn
    -0.60
     ſans
    -0.60
    POSITIVE LOGITS
     cleaning
    0.31
     cleaned
    0.29
    ewoo
    0.28
     tak
    0.28
    cleaned
    0.27
     Braut
    0.26
     said
    0.26
    LabelTagHelper
    0.26
     nek
    0.26
    HasAnnotation
    0.26
    Act Density 0.024%

    No Known Activations