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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geb
    -0.08
    aras
    -0.07
     QRect
    -0.06
     دقی
    -0.06
    ndern
    -0.06
     Jeh
    -0.06
    刻
    -0.06
     datatype
    -0.06
     pleasing
    -0.06
    Wal
    -0.06
    POSITIVE LOGITS
    щи
    0.06
    ughs
    0.06
    ických
    0.06
    ouncement
    0.06
     พฤษภาคม
    0.06
    'a
    0.06
    .disk
    0.06
    clarations
    0.06
    eted
    0.06
     Middleware
    0.06
    Act Density 0.004%

    No Known Activations