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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    यदि
    -0.08
    도로
    -0.08
     आपके
    -0.07
     presenter
    -0.07
    ניים
    -0.07
     यदि
    -0.07
    .Act
    -0.07
    Achievements
    -0.07
     Glob
    -0.07
     presenters
    -0.07
    POSITIVE LOGITS
     cuáles
    0.09
     grem
    0.08
     kamu
    0.08
     VALID
    0.08
     boyunca
    0.07
     izg
    0.07
     financiar
    0.07
     owe
    0.07
     quais
    0.07
     bi
    0.07
    Act Density 0.023%

    No Known Activations