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

    Neuronpedia

    INDEX
    Explanations

    lines or sections that contain comments or instructional notes in code

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

    code comments and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.55
    tagHelperRunner
    -0.52
     lenker
    -0.50
    findpost
    -0.49
    ueger
    -0.49
    extAlignment
    -0.49
    __::
    -0.49
     BOUR
    -0.48
     ujednoznacz
    -0.48
     distin
    -0.47
    POSITIVE LOGITS
     Wikiseite
    0.48
     następ
    0.45
     sorpresas
    0.45
     informée
    0.43
     plegable
    0.43
     nasled
    0.42
     problemów
    0.42
     Überras
    0.41
     leeren
    0.41
     nächsten
    0.40
    Act Density 0.008%

    No Known Activations