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

    Neuronpedia

    INDEX
    Explanations

    died

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    词
    -0.73
    詞
    -0.62
    createStatement
    -0.52
    Challenge
    -0.51
     Challenge
    -0.49
     cena
    -0.47
    zech
    -0.46
     lacking
    -0.46
     challenge
    -0.46
    en
    -0.45
    POSITIVE LOGITS
    SharedDtor
    0.70
     تضيفلها
    0.70
    
    0.69
    Tikang
    0.69
     محفوظة
    0.68
    Jereo
    0.67
     transférez
    0.66
    PerformLayout
    0.65
    ніципалі
    0.65
    SharedCtor
    0.64
    Act Density 0.050%

    No Known Activations