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

    Neuronpedia

    INDEX
    Explanations

    mentions of software modules or components

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

    module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aless
    -0.37
    fgets
    -0.37
    ="@+
    -0.36
    PullParser
    -0.36
    ргани
    -0.35
    libatkan
    -0.34
     artistique
    -0.33
     asciug
    -0.33
    jang
    -0.33
     Venedig
    -0.33
    POSITIVE LOGITS
    Module
    3.41
     Module
    2.81
     Modules
    2.23
     module
    2.22
    module
    2.11
     MODULE
    2.09
     modules
    2.02
    Modules
    1.99
    MODULE
    1.98
     Modul
    1.77
    Act Density 0.006%

    No Known Activations