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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming functions and data processing

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

    Code context: function definitions and parameters

    np_acts-logits-general · gemini-2.0-flash

    success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.81
    BagLayout
    -0.49
     Wikispecies
    -0.48
     aastal
    -0.48
    romeo
    -0.47
    edx
    -0.47
    interopRequire
    -0.47
    alei
    -0.46
    localctx
    -0.46
    IntoConstraints
    -0.45
    POSITIVE LOGITS
     success
    0.88
     succeed
    0.85
     مرئيه
    0.77
     succeeds
    0.77
    Success
    0.75
    success
    0.75
     Success
    0.74
    succeed
    0.73
    featureID
    0.72
     succès
    0.71
    Act Density 0.161%

    No Known Activations