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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    約
    -0.09
    �
    -0.09
     約
    -0.09
    ：約
    -0.08
    (confirm
    -0.08
    约
    -0.07
     Conditioner
    -0.07
     약
    -0.07
    光
    -0.07
     নিশ্চ
    -0.07
    POSITIVE LOGITS
     vergleichen
    0.09
    指标
    0.09
     срав
    0.09
     calculators
    0.09
     từng
    0.09
     countries
    0.09
     vergelijken
    0.08
     calculation
    0.08
     exercise
    0.08
     താര
    0.08
    Act Density 0.019%

    No Known Activations