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

    Neuronpedia

    INDEX
    Explanations

    예

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subsidi
    -0.07
     sert
    -0.07
    民主
    -0.07
    	path
    -0.06
    _Part
    -0.06
    _channel
    -0.06
     título
    -0.06
     channel
    -0.06
     Điện
    -0.06
     wegen
    -0.06
    POSITIVE LOGITS
     예
    0.09
     vä
    0.07
     untrue
    0.07
     readily
    0.07
     cry
    0.07
     najle
    0.07
     possible
    0.07
    odyn
    0.06
     预
    0.06
     زیرا
    0.06
    Act Density 0.003%

    No Known Activations