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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    segment
    -0.07
     Consortium
    -0.07
    %@",
    -0.07
    ookie
    -0.06
    通用
    -0.06
    网
    -0.06
    ᶜ
    -0.06
    Sony
    -0.06
    ============
    -0.06
    אוטומטי
    -0.06
    POSITIVE LOGITS
     Rent
    0.07
    蒎
    0.07
    涨价
    0.07
    海盗
    0.07
     nieruchomości
    0.07
     yearly
    0.07
     angels
    0.07
    Winter
    0.07
     Purchase
    0.07
    earth
    0.07
    Act Density 0.251%

    No Known Activations