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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ших
    -0.07
    decor
    -0.06
    𧿹
    -0.06
    想象
    -0.06
    образ
    -0.06
    ineTransform
    -0.06
    Teachers
    -0.06
     Nvidia
    -0.06
    佼
    -0.06
    POSITIVE LOGITS
     RX
    0.07
    这一年
    0.07
    娠
    0.07
    틉
    0.07
    里斯
    0.07
     DIRECTORY
    0.06
    裙
    0.06
     Trailer
    0.06
     compile
    0.06
    (acc
    0.06
    Act Density 1.910%

    No Known Activations