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

    Neuronpedia

    INDEX
    Explanations

    doi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wallace
    -0.08
     Fill
    -0.07
    电器
    -0.07
    .Con
    -0.07
    placement
    -0.07
     Created
    -0.07
    企业的
    -0.07
     Well
    -0.07
     AVC
    -0.07
    ']
↵
    -0.07
    POSITIVE LOGITS
    ör
    0.06
    球迷
    0.06
    coord
    0.06
    实施方案
    0.06
     processing
    0.06
    _Output
    0.06
    liğini
    0.06
    נוע
    0.06
    不幸
    0.06
    .TableLayoutPanel
    0.06
    Act Density 0.001%

    No Known Activations