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
     shepherd
    -0.07
    增
    -0.07
    绿化
    -0.07
    겴
    -0.07
    رص
    -0.06
     sow
    -0.06
    闻
    -0.06
     offend
    -0.06
     hearty
    -0.06
    noon
    -0.06
    POSITIVE LOGITS
     Analy
    0.08
    ቶ
    0.07
    'util
    0.07
     Tuple
    0.07
     Simpl
    0.07
    |
↵
    0.07
    canonical
    0.07
    _QU
    0.07
    _formats
    0.07
    _write
    0.07
    Act Density 0.004%

    No Known Activations