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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蹑
    -0.07
    一只手
    -0.07
    嚅
    -0.07
     Antony
    -0.07
     använd
    -0.07
    迓
    -0.07
    精彩
    -0.07
    imag
    -0.07
     партнер
    -0.07
     acompaña
    -0.07
    POSITIVE LOGITS
    ද
    0.08
     gladly
    0.06
    fan
    0.06
    .ctrl
    0.06
    stock
    0.06
     Glory
    0.06
     Preferred
    0.06
     Locations
    0.06
     Location
    0.06
    学校的
    0.06
    Act Density 0.001%

    No Known Activations