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

    Neuronpedia

    INDEX
    Explanations

    bounding box data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )::
    -0.07
    מאבק
    -0.07
    🕔
    -0.07
    Ӆ
    -0.07
    知
    -0.07
    )value
    -0.07
    :model
    -0.07
    ➮
    -0.06
    								
↵
    -0.06
    סט
    -0.06
    POSITIVE LOGITS
     диаг
    0.07
    Rights
    0.07
    ileo
    0.07
     التع
    0.07
     AW
    0.07
     tranqu
    0.07
     경
    0.07
    _ce
    0.07
     Coun
    0.06
     הקר
    0.06
    Act Density 0.016%

    No Known Activations