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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    劳
    -0.06
     زی
    -0.06
    师
    -0.06
    isempty
    -0.06
     gói
    -0.06
    Wins
    -0.06
     взгляд
    -0.06
     تف
    -0.06
     lowers
    -0.06
     уров
    -0.06
    POSITIVE LOGITS
     ECS
    0.07
    DataContext
    0.07
     conhec
    0.06
     George
    0.06
    orestation
    0.06
    ather
    0.06
     whereas
    0.06
     approximate
    0.06
     ASA
    0.06
     bip
    0.06
    Act Density 0.032%

    No Known Activations