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

    Neuronpedia

    INDEX
    Explanations

    FL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    projects
    -0.07
    盯
    -0.07
    finalize
    -0.07
     pace
    -0.07
    態度
    -0.06
    当前位置
    -0.06
    lopen
    -0.06
    dz
    -0.06
    DS
    -0.06
    iffs
    -0.06
    POSITIVE LOGITS
    玉米
    0.07
    These
    0.07
     cà
    0.07
     сы
    0.07
    -com
    0.07
     khẳng
    0.07
     Hollow
    0.07
    Corn
    0.07
     vegetable
    0.07
    歃
    0.07
    Act Density 0.346%

    No Known Activations