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

    Neuronpedia

    INDEX
    Explanations

    (=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     troubleshooting
    -0.07
    ная
    -0.07
    .nih
    -0.07
     alot
    -0.06
     nale
    -0.06
     apologise
    -0.06
     abide
    -0.06
    DevExpress
    -0.06
     nominate
    -0.06
    ypsy
    -0.06
    POSITIVE LOGITS
     Δ
    0.08
     hovered
    0.07
     concat
    0.07
    重新
    0.07
     Ш
    0.07
    Modified
    0.07
    强制
    0.07
     RAID
    0.07
     dangerous
    0.07
    READING
    0.07
    Act Density 0.002%

    No Known Activations