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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     исход
    -0.07
    Flat
    -0.07
     lil
    -0.07
     Bren
    -0.07
     Dee
    -0.07
     फर
    -0.06
     बदल
    -0.06
     mặt
    -0.06
    [*
    -0.06
    .rawValue
    -0.06
    POSITIVE LOGITS
    aily
    0.07
     dump
    0.06
    LOB
    0.06
    Third
    0.06
    uling
    0.06
    \Input
    0.06
     decom
    0.06
     savun
    0.06
    produk
    0.06
     právo
    0.06
    Act Density 0.089%

    No Known Activations