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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    717
    -0.08
    .
    -0.07
    坏
    -0.07
    676
    -0.07
    美國
    -0.06
    525
    -0.06
    硬
    -0.06
    Dados
    -0.06
    ).
    -0.06
    _No
    -0.06
    POSITIVE LOGITS
    .collection
    0.06
    (delta
    0.06
    ότητας
    0.06
    aining
    0.06
    rupt
    0.06
    ルの
    0.06
    _META
    0.06
     Affordable
    0.06
    locked
    0.05
    _menus
    0.05
    Act Density 0.018%

    No Known Activations