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

    Neuronpedia

    INDEX
    Explanations

    transform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    wizard
    -0.07
    шт
    -0.07
    Hdr
    -0.06
     Voter
    -0.06
    ümüzde
    -0.06
    ัตถ
    -0.06
    оке
    -0.06
     Tabs
    -0.06
     Poland
    -0.06
    POSITIVE LOGITS
    ��
    0.06
     التح
    0.06
     hend
    0.06
     jLabel
    0.06
    二
    0.06
     crumbling
    0.06
    ><![
    0.06
     �
    0.05
    ieee
    0.05
     文章
    0.05
    Act Density 0.017%

    No Known Activations