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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نوع
    -0.07
    罾
    -0.07
    烈
    -0.07
     vbCrLf
    -0.07
    atore
    -0.07
    แนว
    -0.07
    上升
    -0.07
     blond
    -0.06
    所謂
    -0.06
    rians
    -0.06
    POSITIVE LOGITS
    enum
    0.07
    Must
    0.07
    只怕
    0.06
    },${
    0.06
    (HWND
    0.06
     VM
    0.06
     Lee
    0.06
     madness
    0.06
    맏
    0.06
    .shutdown
    0.06
    Act Density 0.094%

    No Known Activations