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

    Neuronpedia

    INDEX
    Explanations

    Summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /vnd
    -0.07
     opponent
    -0.06
     náměstí
    -0.06
    ่นเกม
    -0.06
     rew
    -0.06
    _pattern
    -0.06
    _broadcast
    -0.06
     آز
    -0.06
    ichier
    -0.06
    _nested
    -0.06
    POSITIVE LOGITS
    Summary
    0.11
    SUM
    0.08
     Summary
    0.08
    .Sum
    0.07
     undermines
    0.06
    Tbl
    0.06
    Britain
    0.06
     Blogs
    0.06
    Miami
    0.06
     advisable
    0.06
    Act Density 0.004%

    No Known Activations