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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JS
    -0.07
    尚
    -0.06
    ,param
    -0.06
    nest
    -0.06
    ользоват
    -0.06
    azen
    -0.06
    kt
    -0.06
    PF
    -0.06
    泛
    -0.06
    War
    -0.06
    POSITIVE LOGITS
     lỗi
    0.07
    .DriverManager
    0.07
    ी↵
    0.07
     chuyện
    0.06
     memcmp
    0.06
    _mob
    0.06
     MatDialog
    0.06
     permalink
    0.06
    thesized
    0.06
     プロ
    0.06
    Act Density 0.015%

    No Known Activations