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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loft
    -0.07
    _tok
    -0.06
    iffer
    -0.06
    弨
    -0.06
    ��
    -0.06
    יבל
    -0.06
    פרי
    -0.06
    Saudi
    -0.06
     nieuwe
    -0.06
    _smooth
    -0.06
    POSITIVE LOGITS
    /payment
    0.07
     Lesson
    0.07
    	left
    0.07
     horrors
    0.07
     doesn
    0.07
     tyr
    0.07
    每个
    0.07
    一半
    0.06
    vertise
    0.06
    伤亡
    0.06
    Act Density 0.002%

    No Known Activations