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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writes
    -0.06
     FFT
    -0.06
    Mary
    -0.06
    灭
    -0.06
    .decorators
    -0.06
    雪
    -0.06
     Rachel
    -0.06
     truy
    -0.06
    _Texture
    -0.06
     Obl
    -0.06
    POSITIVE LOGITS
     stato
    0.07
    :title
    0.07
     conocer
    0.07
     seam
    0.06
    _FILE
    0.06
    .BorderSize
    0.06
     sut
    0.06
     uvol
    0.06
    ınma
    0.06
    ={{↵
    0.06
    Act Density 0.034%

    No Known Activations