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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    進入
    -0.07
     jihadist
    -0.07
    细微
    -0.07
    뻔
    -0.07
     Bench
    -0.07
    *u
    -0.07
    نظ
    -0.07
     dunk
    -0.07
    头顶
    -0.07
    卖掉
    -0.06
    POSITIVE LOGITS
     worlds
    0.07
     Errors
    0.07
    フレ
    0.07
    いっぱ
    0.07
     self
    0.07
    opts
    0.07
    roupe
    0.07
    licer
    0.07
    */)↵
    0.07
     .....
    0.07
    Act Density 0.135%

    No Known Activations