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

    Neuronpedia

    INDEX
    Explanations

    references to modular components or systems

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

    technical module descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.45
    (");
    -0.42
    printStackTrace
    -0.41
     Goodrich
    -0.41
    Getty
    -0.40
    참고
    -0.40
     najleps
    -0.40
    <b>
    -0.38
     Navidad
    -0.38
     négatif
    -0.38
    POSITIVE LOGITS
     module
    2.23
     Module
    2.14
     modules
    1.98
     Modules
    1.91
    Module
    1.88
    module
    1.78
     MODULE
    1.75
    Modules
    1.55
    MODULE
    1.52
    模块
    1.50
    Act Density 0.014%

    No Known Activations