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

    Neuronpedia

    INDEX
    Explanations

    file paths and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spring
    -0.08
    ssl
    -0.07
     Berger
    -0.07
    虔
    -0.07
    \Tests
    -0.07
    (db
    -0.07
    敏感
    -0.07
    uous
    -0.07
    spot
    -0.07
    贯通
    -0.07
    POSITIVE LOGITS
    income
    0.08
    הוצאה
    0.07
    fault
    0.07
    (Input
    0.06
    Assembler
    0.06
    无敌
    0.06
     throwError
    0.06
    .oper
    0.06
    _Element
    0.06
    老爸
    0.06
    Act Density 0.018%

    No Known Activations