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
    _texts
    -0.06
    ych
    -0.06
    Forg
    -0.06
    .setY
    -0.06
     electricity
    -0.06
    gx
    -0.06
     nhạc
    -0.06
    فش
    -0.06
    IVITY
    -0.06
    бом
    -0.06
    POSITIVE LOGITS
    centaje
    0.07
     DECLARE
    0.07
    (emp
    0.07
     lined
    0.06
    ाहन
    0.06
    ültür
    0.06
     spoiled
    0.06
    #↵↵
    0.06
     ↵    ↵
    0.06
    Republican
    0.06
    Act Density 0.029%

    No Known Activations