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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    me
    -0.07
    רוב
    -0.07
     đầu
    -0.07
    ลง
    -0.07
    .dm
    -0.07
    屠
    -0.07
     Comb
    -0.07
    宿
    -0.06
    但他
    -0.06
    ่ม
    -0.06
    POSITIVE LOGITS
    גיר
    0.07
    .fixed
    0.07
    设置
    0.07
     flashed
    0.07
    .orders
    0.07
     Pixels
    0.07
    ybrid
    0.06
    十七
    0.06
    avras
    0.06
    _wall
    0.06
    Act Density 0.010%

    No Known Activations