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

    Neuronpedia

    INDEX
    Explanations

    Question answering/editing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McCabe
    -0.07
     oslo
    -0.07
     İşte
    -0.07
    ाप
    -0.06
     yerleş
    -0.06
    Пол
    -0.06
     faut
    -0.06
     onload
    -0.06
     общ
    -0.06
     Groups
    -0.06
    POSITIVE LOGITS
    极
    0.07
    �
    0.07
     selling
    0.06
    خ
    0.06
    ?.
    0.06
    栏
    0.06
    инг
    0.06
     blue
    0.06
     win
    0.06
     кар
    0.06
    Act Density 0.000%

    No Known Activations