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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Method
    -0.07
    จำ
    -0.07
    Highest
    -0.07
     meny
    -0.07
    香港
    -0.06
    _smart
    -0.06
     Monter
    -0.06
    挂
    -0.06
    候
    -0.06
     noodles
    -0.06
    POSITIVE LOGITS
    @admin
    0.06
     حافظ
    0.06
    ">*</
    0.06
     Але
    0.06
    ”.↵↵
    0.06
    існо
    0.06
     unjust
    0.06
    _pins
    0.06
    ALLERY
    0.06
    lav
    0.06
    Act Density 0.075%

    No Known Activations