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

    Neuronpedia

    INDEX
    Explanations

    references to programming modules and their components

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

    "Module" or "modules"

    np_acts-logits-general · gemini-2.0-flash

    module followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goodrich
    -0.47
    EDEFAULT
    -0.36
    (");
    -0.35
     Prensa
    -0.35
    Sainte
    -0.35
     Venedig
    -0.35
    printStackTrace
    -0.34
     Úl
    -0.34
     Privacidad
    -0.34
     najleps
    -0.34
    POSITIVE LOGITS
     module
    2.72
     Module
    2.70
    module
    2.56
    Module
    2.56
     modules
    2.47
     Modules
    2.45
     MODULE
    2.23
    modules
    2.14
    Modules
    2.11
    MODULE
    2.09
    Act Density 0.078%

    No Known Activations