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

    Neuronpedia

    INDEX
    Explanations

    Foreign language articles/pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guys
    -0.07
     Variable
    -0.06
     for
    -0.06
    026
    -0.06
     IActionResult
    -0.06
    '↵↵↵
    -0.06
     alumno
    -0.06
     Ion
    -0.06
     Clarence
    -0.06
     towards
    -0.06
    POSITIVE LOGITS
     que
    0.07
     которое
    0.07
     которая
    0.07
     osób
    0.07
     che
    0.07
     prevailed
    0.07
     která
    0.07
    _mt
    0.06
    .TRAN
    0.06
     eliminated
    0.06
    Act Density 0.031%

    No Known Activations