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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пот
    -0.07
     зрения
    -0.07
    });↵↵
    -0.06
    >[↵
    -0.06
     france
    -0.06
    explo
    -0.06
     Choi
    -0.06
    iere
    -0.06
    ��
    -0.06
    fts
    -0.06
    POSITIVE LOGITS
    orges
    0.07
    (Parcel
    0.07
    =document
    0.07
     precise
    0.06
    漫画
    0.06
    _possible
    0.06
    本当
    0.06
     JOHN
    0.06
     하고
    0.06
     законом
    0.06
    Act Density 0.001%

    No Known Activations