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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure in code

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

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.52
     IBOutlet
    -0.50
     nemlig
    -0.50
    Portály
    -0.49
    -------------</
    -0.49
     čierna
    -0.48
     čier
    -0.47
     tiegħek
    -0.45
    Демографія
    -0.45
     zijne
    -0.44
    POSITIVE LOGITS
     Pon
    0.49
    AccessorTable
    0.43
    ALLES
    0.42
     gild
    0.42
     GTP
    0.42
     …
    0.41
     Sage
    0.41
     slings
    0.40
    Chem
    0.40
     Snake
    0.40
    Act Density 0.050%

    No Known Activations