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

    Neuronpedia

    INDEX
    Explanations

    import altair as alt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arton
    -0.09
     Legion
    -0.09
     Eisen
    -0.09
    erin
    -0.09
    ajas
    -0.09
     Dra
    -0.09
    imin
    -0.09
    UCT
    -0.08
     toolbar
    -0.08
     punishable
    -0.08
    POSITIVE LOGITS
     st
    0.26
    (st
    0.16
     ÑģÑĤ
    0.15
    .st
    0.14
    \tst
    0.13
    _st
    0.12
    ,st
    0.12
     ste
    0.12
     St
    0.12
     ST
    0.11
    Act Density 0.015%

    No Known Activations