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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bearing
    -0.07
    钢板
    -0.07
    锿
    -0.07
    雪山
    -0.07
    更低
    -0.06
    铽
    -0.06
    并未
    -0.06
     AU
    -0.06
    舆
    -0.06
     shown
    -0.06
    POSITIVE LOGITS
     meanwhile
    0.07
    ünde
    0.07
     Destiny
    0.07
    用了
    0.07
    ལ
    0.07
     decoding
    0.07
    ionage
    0.07
     weekday
    0.06
    ucky
    0.06
    add
    0.06
    Act Density 0.013%

    No Known Activations