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

    Neuronpedia

    INDEX
    Explanations

    Etymology and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     converters
    -0.07
     subscribed
    -0.07
     bubbles
    -0.07
    -open
    -0.07
    ↓
    -0.07
     Cases
    -0.06
     arterial
    -0.06
    增持
    -0.06
    resources
    -0.06
     owe
    -0.06
    POSITIVE LOGITS
    ErrorException
    0.08
     CREATED
    0.07
    ⼝
    0.07
    (lst
    0.07
    쾃
    0.07
    睎
    0.07
    nego
    0.06
    GMEM
    0.06
     embroid
    0.06
     EN
    0.06
    Act Density 0.009%

    No Known Activations