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

    Neuronpedia

    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Presidential
    -0.07
    .bz
    -0.07
     Kits
    -0.07
    켓
    -0.07
     cherry
    -0.07
    陈
    -0.06
    _APB
    -0.06
     exhausting
    -0.06
     protože
    -0.06
    Parts
    -0.06
    POSITIVE LOGITS
    (false
    0.07
    원이
    0.06
    _TOTAL
    0.06
     dpi
    0.06
     реак
    0.06
    яет
    0.06
    ↵↵↵↵↵↵
    0.06
     serif
    0.06
     Editorial
    0.06
     There
    0.06
    Act Density 0.011%

    No Known Activations