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

    Neuronpedia

    INDEX
    Explanations

    the or your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precisely
    -0.07
    edriver
    -0.07
    蔬
    -0.07
     JO
    -0.06
    棨
    -0.06
    民航
    -0.06
     lush
    -0.06
    睢
    -0.06
     via
    -0.06
    毙
    -0.06
    POSITIVE LOGITS
     Shuffle
    0.08
    工作方案
    0.07
    _iteration
    0.07
     Retreat
    0.07
    VERSION
    0.07
    شهور
    0.07
    𝐚
    0.07
     بدأت
    0.07
     apartment
    0.07
     gsi
    0.07
    Act Density 0.071%

    No Known Activations