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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Helvetica
    -0.09
     hors
    -0.08
     closely
    -0.08
     गया
    -0.07
     proximity
    -0.07
     observation
    -0.07
     confianza
    -0.07
     oku
    -0.07
     aden
    -0.07
     hovering
    -0.07
    POSITIVE LOGITS
    0.08
     quartos
    0.08
    (total
    0.08
    သော
    0.08
    分彩
    0.08
     ของ
    0.08
    割合
    0.08
    (cart
    0.08
     tears
    0.08
     гэтага
    0.08
    Act Density 0.028%
    No Known Activations