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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rus
    -0.07
     forfeiture
    -0.07
    avior
    -0.06
    stackpath
    -0.06
     mf
    -0.06
    干
    -0.06
     segments
    -0.06
     assembled
    -0.06
     revolutions
    -0.06
     yummy
    -0.05
    POSITIVE LOGITS
     (:
    0.08
    .HttpStatus
    0.07
    class
    0.07
    msgid
    0.07
    松
    0.07
     začal
    0.07
    мотреть
    0.07
    //}↵↵
    0.07
    CSS
    0.07
    ando
    0.07
    Act Density 0.000%

    No Known Activations