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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     North
    -0.06
     Water
    -0.06
     位
    -0.06
     villain
    -0.06
    -with
    -0.06
     Cut
    -0.06
    centration
    -0.06
     puzzle
    -0.06
     Combine
    -0.06
     follows
    -0.05
    POSITIVE LOGITS
     перевір
    0.07
     количества
    0.07
    ائد
    0.07
    엔
    0.07
    (scene
    0.06
    Similarly
    0.06
     clit
    0.06
    _questions
    0.06
     متفاوت
    0.06
    илась
    0.06
    Act Density 0.031%

    No Known Activations