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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (turn
    -0.07
    ениях
    -0.07
     bigot
    -0.06
    夫
    -0.06
    /source
    -0.06
    _____
    -0.06
    _PADDING
    -0.06
    _tA
    -0.06
    BUR
    -0.06
    MOST
    -0.06
    POSITIVE LOGITS
     Calibration
    0.07
     discret
    0.07
    644
    0.07
     CCD
    0.06
     RPG
    0.06
    (if
    0.06
    .lua
    0.06
     appell
    0.06
     spurred
    0.06
    StrLn
    0.06
    Act Density 0.003%

    No Known Activations