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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    part
    -0.09
     الرجل
    -0.08
    秘诀
    -0.08
     gadgets
    -0.08
     ;)↵↵
    -0.08
    二维
    -0.08
    optimized
    -0.08
    meister
    -0.08
    ालत
    -0.08
     dzięki
    -0.08
    POSITIVE LOGITS
     승인
    0.13
     मंज
    0.11
    批准
    0.11
     discretion
    0.11
     अदालत
    0.10
     withholding
    0.10
     আদাল
    0.10
     waiver
    0.10
    司法
    0.10
     issuance
    0.10
    Act Density 0.022%

    No Known Activations