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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     동안
    -0.08
    ّا
    -0.08
     industry's
    -0.07
    .rand
    -0.07
     keto
    -0.07
     Keto
    -0.07
    PIO
    -0.07
     فإن
    -0.07
    ಡಿಯ
    -0.07
    kil
    -0.07
    POSITIVE LOGITS
     élég
    0.09
     गण
    0.08
     calculations
    0.08
     ગણ
    0.08
    分析
    0.08
     воспольз
    0.08
    ละเอียด
    0.08
     approaches
    0.08
     ари
    0.08
     elabor
    0.08
    Act Density 0.136%

    No Known Activations