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

    Neuronpedia

    INDEX
    Explanations

    Time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cha
    -0.07
    Corner
    -0.06
    Fran
    -0.06
     Trang
    -0.06
    振り
    -0.06
     songwriter
    -0.06
    Bulk
    -0.06
    Interpolator
    -0.06
     Fayette
    -0.06
    unc
    -0.06
    POSITIVE LOGITS
    caffold
    0.07
     iterable
    0.07
     AR
    0.07
    ↵                ↵
    0.06
    ندا
    0.06
    Nuitka
    0.06
     minutes
    0.06
     Dabei
    0.06
    公開
    0.06
     '-')
    0.06
    Act Density 0.008%

    No Known Activations