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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tp
    -0.07
    "He
    -0.07
    베
    -0.06
    ازات
    -0.06
     CONTRIBUTORS
    -0.06
    щей
    -0.06
    ьют
    -0.06
    persons
    -0.06
     економ
    -0.06
    Compare
    -0.06
    POSITIVE LOGITS
     Creation
    0.07
    IMS
    0.06
    _bed
    0.06
    ilik
    0.06
    .LINE
    0.06
     Xperia
    0.06
    Apart
    0.06
    _RENDER
    0.06
     creation
    0.06
    alex
    0.06
    Act Density 0.108%

    No Known Activations