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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hanging
    -0.06
    319
    -0.06
    рощ
    -0.06
    谢
    -0.06
    ercul
    -0.06
    sweet
    -0.06
    fect
    -0.06
    ------------
    -0.06
    antic
    -0.06
     something
    -0.06
    POSITIVE LOGITS
     prototype
    0.07
    <y
    0.06
     inhibitor
    0.06
    主義
    0.06
    charts
    0.06
    (Op
    0.06
     explor
    0.06
    <Service
    0.06
    جی
    0.06
    <File
    0.06
    Act Density 0.001%

    No Known Activations