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

    Neuronpedia

    INDEX
    Explanations

    months and seasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aside
    -0.07
    政府采购
    -0.07
    bilité
    -0.07
    二十
    -0.06
     intrig
    -0.06
    岗位
    -0.06
     assists
    -0.06
    .swap
    -0.06
     humanitarian
    -0.06
    /views
    -0.06
    POSITIVE LOGITS
    ром
    0.07
     torrent
    0.06
    sched
    0.06
    鬷
    0.06
    	thread
    0.06
    �
    0.06
     >/
    0.06
    ❇
    0.06
     zz
    0.06
    ]bool
    0.06
    Act Density 0.010%

    No Known Activations