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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    信号
    -0.07
     flavorful
    -0.06
    串联
    -0.06
     gez
    -0.06
    �
    -0.06
     tài
    -0.06
    (ps
    -0.06
    練
    -0.06
    .SET
    -0.06
    為
    -0.06
    POSITIVE LOGITS
     rửa
    0.08
    哢
    0.08
     תמיד
    0.08
    工商局
    0.07
    変え
    0.07
     cigarette
    0.07
     שאני
    0.06
    箨
    0.06
     onChanged
    0.06
    Witness
    0.06
    Act Density 0.080%

    No Known Activations