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

    Neuronpedia

    INDEX
    Explanations

    questions and responses related to confirmation or validation

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

    Determining truth of statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.69
     مشين
    -0.66
    ParallelGroup
    -0.65
     BoxDecoration
    -0.64
    UserScript
    -0.64
     समीक्षाएं
    -0.63
    ChildScrollView
    -0.62
    ArgumentParser
    -0.59
    RegressionTest
    -0.59
     initComponents
    -0.59
    POSITIVE LOGITS
     yes
    0.67
     YES
    0.54
     Yes
    0.54
    Yes
    0.52
    yes
    0.52
    YES
    0.47
     yeah
    0.41
     false
    0.39
    SU
    0.39
    Oui
    0.38
    Act Density 0.055%

    No Known Activations