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

    Neuronpedia

    INDEX
    Explanations

    Medical grades/scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isson
    -0.07
    들
    -0.07
     Climate
    -0.07
    פר
    -0.07
    üsseldorf
    -0.06
    UTC
    -0.06
     Aer
    -0.06
    的时间
    -0.06
    .debug
    -0.06
     призна
    -0.06
    POSITIVE LOGITS
    vecs
    0.07
    扊
    0.07
    _advance
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    Ủ
    0.06
    _LAT
    0.06
    产销
    0.06
    UsingEncoding
    0.06
    �
    0.06
    碨
    0.06
    Act Density 0.014%

    No Known Activations