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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     책
    -0.08
     Holmes
    -0.07
     Moves
    -0.07
     forensic
    -0.07
     Leakage
    -0.07
     AUTHOR
    -0.07
     mount
    -0.06
    ROWS
    -0.06
     Booking
    -0.06
     verbosity
    -0.06
    POSITIVE LOGITS
    ("//*[@
    0.07
     pprint
    0.06
    derive
    0.06
    b
    0.06
    .GL
    0.06
     в
    0.06
    youtu
    0.06
     tick
    0.06
    slope
    0.06
    bol
    0.06
    Act Density 0.008%

    No Known Activations