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

    Neuronpedia

    INDEX
    Explanations

    code-related terms, specifically focused on programming languages and source files

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

    technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     treno
    -0.39
    ruik
    -0.38
    warten
    -0.37
     pungkasnya
    -0.36
     zufolge
    -0.36
     Wallflower
    -0.35
     sengaja
    -0.35
    DataAnnotations
    -0.35
    uette
    -0.35
     asupra
    -0.35
    POSITIVE LOGITS
    Autoritní
    0.87
     utafitiHapana
    0.67
    ToRefresh
    0.65
     }{@
    0.65
    最快更新
    0.60
    出版年
    0.57
    oa̍t
    0.56
     otomatig
    0.56
    FileDescriptor
    0.56
     <=",
    0.54
    Act Density 0.007%

    No Known Activations