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

    Neuronpedia

    INDEX
    Explanations

    Movie/TV plots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    希望大家
    -0.07
     아니다
    -0.07
     מאד
    -0.07
     저는
    -0.07
    之中
    -0.07
    (forms
    -0.07
    なければ
    -0.07
    에
    -0.07
    福祉
    -0.07
     منه
    -0.07
    POSITIVE LOGITS
     Flo
    0.08
    _SH
    0.07
    蹿
    0.07
     Hö
    0.07
    赔
    0.07
     ashamed
    0.07
     Compile
    0.06
    _override
    0.06
     starvation
    0.06
    products
    0.06
    Act Density 0.191%

    No Known Activations