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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    交
    -0.08
    QUAL
    -0.08
     RECORD
    -0.07
    眵
    -0.07
    所需
    -0.07
    CARD
    -0.07
    aturdays
    -0.07
    痢
    -0.07
     tensor
    -0.07
     순
    -0.07
    POSITIVE LOGITS
    丹麦
    0.07
     parece
    0.07
     este
    0.07
    ",↵↵
    0.07
    一期
    0.07
     Occ
    0.07
    FileInfo
    0.06
     link
    0.06
     getMessage
    0.06
    ()}</
    0.06
    Act Density 0.014%

    No Known Activations