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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCORE
    -0.06
    _redirect
    -0.06
    Veter
    -0.06
    рет
    -0.06
     renovation
    -0.06
     McK
    -0.06
    _board
    -0.06
    dirty
    -0.06
    vin
    -0.06
    lio
    -0.06
    POSITIVE LOGITS
    :maj
    0.07
     indeed
    0.06
     із
    0.06
    \Admin
    0.06
     Regiment
    0.06
    ighter
    0.06
    ibre
    0.06
    σαν
    0.06
    इन
    0.06
     attributed
    0.06
    Act Density 0.037%

    No Known Activations