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

    Neuronpedia

    INDEX
    Explanations

    Quoted text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fixed
    -0.07
    _until
    -0.07
    ก
    -0.07
     Injection
    -0.07
     honorary
    -0.07
     spinning
    -0.06
     betrayed
    -0.06
    Основ
    -0.06
    _VISIBLE
    -0.06
    ーパー
    -0.06
    POSITIVE LOGITS
     tedbir
    0.06
     اینتر
    0.06
    �
    0.06
    館
    0.06
    inheritDoc
    0.06
     adher
    0.06
     플
    0.06
    บาท
    0.06
     Dinner
    0.06
    佳
    0.06
    Act Density 0.049%

    No Known Activations