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

    Neuronpedia

    INDEX
    Explanations

    grammatical inversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sequential
    -0.09
     Sequential
    -0.08
    w
    -0.08
     sequential
    -0.08
    бей
    -0.08
    Orden
    -0.08
    orientation
    -0.08
    -0.07
     exhibit
    -0.07
     W
    -0.07
    POSITIVE LOGITS
     olmuş
    0.08
     ocurrido
    0.08
     varen
    0.08
     سعر
    0.08
    akash
    0.08
     "'"
    0.08
    탈
    0.08
     mansion
    0.07
     zav
    0.07
     يحت
    0.07
    Act Density 0.002%
    No Known Activations