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

    Neuronpedia

    INDEX
    Explanations

    improvements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _limit
    -0.07
     tk
    -0.07
     produits
    -0.06
    locate
    -0.06
     cool
    -0.06
     Sender
    -0.06
     pentru
    -0.06
    uez
    -0.06
    ści
    -0.06
    eneration
    -0.06
    POSITIVE LOGITS
    湯
    0.06
    (\$
    0.06
    flags
    0.06
    新的
    0.06
     trafficking
    0.06
     Πολ
    0.06
    (cljs
    0.05
    (KERN
    0.05
     дина
    0.05
     paddle
    0.05
    Act Density 0.000%

    No Known Activations