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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Work
    -0.07
    aps
    -0.06
    :absolute
    -0.06
    fortunately
    -0.06
     antagonist
    -0.06
    UGIN
    -0.06
     Duty
    -0.06
     guardar
    -0.06
     sophistic
    -0.06
     unbe
    -0.06
    POSITIVE LOGITS
     목
    0.07
     MAIL
    0.07
    姓名
    0.06
     ارتباط
    0.06
     А
    0.06
    017
    0.06
    008
    0.06
     execute
    0.06
    operand
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations