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

    Neuronpedia

    INDEX
    Explanations

    ellipsis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neces
    -0.10
    _nums
    -0.07
    IEW
    -0.07
    因子
    -0.07
    芑
    -0.07
     Medic
    -0.07
     pumping
    -0.07
    setup
    -0.07
     kiểm
    -0.07
    ﹹ
    -0.07
    POSITIVE LOGITS
     espionage
    0.08
    ספורט
    0.07
    大城市
    0.07
     comboBox
    0.07
     toured
    0.06
    董事会
    0.06
    >")
    0.06
    .inner
    0.06
    ᨨ
    0.06
     Robertson
    0.06
    Act Density 0.009%

    No Known Activations