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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    columns
    -0.07
    cmc
    -0.06
     Ashley
    -0.06
     Stevenson
    -0.06
     developed
    -0.06
     Cro
    -0.06
    ीत
    -0.06
     creams
    -0.06
     собы
    -0.06
     dout
    -0.06
    POSITIVE LOGITS
    LED
    0.07
     يناير
    0.07
    _elim
    0.06
    F
    0.06
     Moz
    0.06
    _ble
    0.06
    Gesture
    0.06
    (lbl
    0.06
    ież
    0.06
     ​​
    0.06
    Act Density 0.011%

    No Known Activations