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

    Neuronpedia

    INDEX
    Explanations

    Programming errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manage
    -0.07
    Friendly
    -0.07
    ผ
    -0.07
     boon
    -0.07
     boost
    -0.07
    忙
    -0.07
     (__
    -0.07
    年中国
    -0.06
    预约
    -0.06
     dr
    -0.06
    POSITIVE LOGITS
     למשל
    0.08
     Tư
    0.07
     disks
    0.07
    *)↵↵
    0.07
     symbols
    0.07
    奶粉
    0.07
    stairs
    0.07
    默默
    0.07
    .dtype
    0.07
    chosen
    0.07
    Act Density 0.003%

    No Known Activations