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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    A token-level detector for legal/administrative content — especially references to permits, filings, and requirements for forming or managing entities and compliance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     }),↵
    -0.06
     mặt
    -0.06
    (cookie
    -0.06
    Domain
    -0.06
     handler
    -0.06
     VIN
    -0.06
     trouvé
    -0.06
    哪
    -0.06
    ViewController
    -0.06
     candy
    -0.06
    POSITIVE LOGITS
    <Integer
    0.08
    ↵↵↵↵↵↵
    0.07
    buquerque
    0.07
    exe
    0.07
    opp
    0.07
    modele
    0.06
    クト
    0.06
    接着
    0.06
     inexpensive
    0.06
    agnost
    0.06
    Act Density 0.108%

    No Known Activations