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

    Neuronpedia

    INDEX
    Explanations

    certainly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discussed
    -0.07
     keyPressed
    -0.06
    aper
    -0.06
    ô
    -0.06
     แก
    -0.06
     blízk
    -0.06
    eden
    -0.06
    achten
    -0.06
    \model
    -0.06
    ाग
    -0.06
    POSITIVE LOGITS
     certainly
    0.09
    .="
    0.07
    enever
    0.07
    ]\
    0.07
     currentUser
    0.07
     AREA
    0.06
    .Tests
    0.06
    来了
    0.06
     数据
    0.06
     food
    0.06
    Act Density 0.003%

    No Known Activations