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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipar
    -0.07
    <Tuple
    -0.07
    ií
    -0.06
    ‌هایی
    -0.06
     Capacity
    -0.06
    uire
    -0.06
    印
    -0.06
     równ
    -0.06
    raq
    -0.06
    ‌های
    -0.06
    POSITIVE LOGITS
    _MOBILE
    0.07
     dovol
    0.06
    _TOGGLE
    0.06
    	model
    0.06
     coupon
    0.06
     cheapest
    0.06
     conversation
    0.06
    二二
    0.06
    .appcompat
    0.06
     mouseClicked
    0.06
    Act Density 0.001%

    No Known Activations