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

    Neuronpedia

    INDEX
    Explanations

    addressing the reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    łe
    -0.07
    程
    -0.07
     آماده
    -0.07
     uninitialized
    -0.06
    -0.06
    附
    -0.06
    raç
    -0.06
    δυ
    -0.06
    (duration
    -0.06
    -0.06
    POSITIVE LOGITS
     위해
    0.07
    �
    0.06
    .Month
    0.06
     rẻ
    0.06
    níky
    0.06
     shale
    0.06
    ойчив
    0.06
     Орг
    0.06
     primeiro
    0.06
    [token
    0.06
    Act Density 0.053%

    No Known Activations