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

    Neuronpedia

    INDEX
    Explanations

    occurrences of module-related terminology in programming language contexts

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

    "module" or "Mod" prefix

    np_acts-logits-general · gemini-2.0-flash

    module and modulation concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    optionalTypeArgs
    -0.43
    駆け
    -0.43
     pinulongan
    -0.41
    glyphicon
    -0.39
    __(/*!
    -0.38
     strain
    -0.38
    impact
    -0.37
    readAs
    -0.37
    ♥♥
    -0.37
     
    -0.36
    POSITIVE LOGITS
     Modules
    0.83
     MODULE
    0.79
     Module
    0.79
    Modules
    0.75
     modules
    0.70
     module
    0.67
    Module
    0.66
    modules
    0.63
     Modul
    0.63
    MODULE
    0.61
    Act Density 0.143%

    No Known Activations