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

    Neuronpedia

    INDEX
    Explanations

    Code, URLs, technical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FA
    -0.07
    니스
    -0.06
    Jake
    -0.06
     Cyr
    -0.06
    511
    -0.06
    bu
    -0.06
     Jake
    -0.06
    ользов
    -0.06
    Ca
    -0.06
     inne
    -0.06
    POSITIVE LOGITS
    .Categories
    0.07
    -font
    0.06
    -labelled
    0.06
     phóng
    0.06
     grass
    0.06
     scrape
    0.06
     stability
    0.06
     chạy
    0.06
    (label
    0.06
    licate
    0.06
    Act Density 0.025%

    No Known Activations