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

    Neuronpedia

    INDEX
    Explanations

    prior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ceptive
    -0.08
     sudoku
    -0.07
    개발
    -0.06
    ();↵↵↵
    -0.06
    ServiceProvider
    -0.06
     вибор
    -0.06
     Tanzania
    -0.06
    っと
    -0.06
     Genel
    -0.06
    alyzed
    -0.06
    POSITIVE LOGITS
    _bits
    0.07
     prior
    0.07
    /shared
    0.07
     panda
    0.07
     зан
    0.06
     iter
    0.06
    走
    0.06
    istence
    0.06
     false
    0.06
    tors
    0.06
    Act Density 0.001%

    No Known Activations