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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure within programming or script files

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

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.46
     
    -0.38
    ądź
    -0.36
    k
    -0.36
    s
    -0.34
     orejas
    -0.32
    amitié
    -0.32
    e
    -0.31
     tollen
    -0.31
    ↵
    -0.30
    POSITIVE LOGITS
     kasarigan
    1.11
     queſta
    1.07
     Италијани
    0.96
    rungsseite
    0.96
     ſind
    0.94
    transQ
    0.90
     Wikimedijinoj
    0.88
     zwiſchen
    0.88
    AISSEE
    0.88
    KommentareTeilen
    0.87
    Act Density 0.011%

    No Known Activations