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

    Neuronpedia

    INDEX
    Explanations

    Special character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stride
    -0.09
     potente
    -0.09
     laminate
    -0.09
     largas
    -0.08
     journals
    -0.08
     starken
    -0.08
     العالية
    -0.08
     Bah
    -0.08
    %B
    -0.08
     Weiterlesen
    -0.08
    POSITIVE LOGITS
    列表
    0.10
    Collection
    0.09
    项
    0.09
    Observe
    0.08
    .union
    0.08
    tolist
    0.08
    -list
    0.08
     Collection
    0.08
    集合
    0.08
    Invite
    0.08
    Act Density 0.023%

    No Known Activations