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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzes
    -0.08
    ǽ
    -0.07
     Indigenous
    -0.07
    🍫
    -0.06
    ossil
    -0.06
    .methods
    -0.06
    땃
    -0.06
    ,www
    -0.06
    ा
    -0.06
    cff
    -0.06
    POSITIVE LOGITS
    杖
    0.08
    主任
    0.07
    olan
    0.07
     sch
    0.07
    给她
    0.07
    (tile
    0.07
     workload
    0.07
    骑行
    0.07
    展位
    0.07
     longevity
    0.07
    Act Density 0.000%

    No Known Activations