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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -sama
    -0.08
    .samples
    -0.07
    .toBe
    -0.07
     Doch
    -0.07
     currentPage
    -0.07
     najbliż
    -0.07
    German
    -0.07
    DTO
    -0.07
    equiv
    -0.07
     kiên
    -0.07
    POSITIVE LOGITS
     Variant
    0.08
    loid
    0.07
    جاز
    0.07
    highlight
    0.07
    ycin
    0.07
     Road
    0.06
    ㄡ
    0.06
    yat
    0.06
    整体
    0.06
    yt
    0.06
    Act Density 0.012%

    No Known Activations