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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anecdotes
    -0.07
     фрон
    -0.07
     sergeant
    -0.06
     KeyEvent
    -0.06
    .Euler
    -0.06
    vědom
    -0.06
    394
    -0.06
    eddar
    -0.06
     Carter
    -0.06
     Swamp
    -0.06
    POSITIVE LOGITS
     групи
    0.07
    marsh
    0.06
    (ids
    0.06
    。
↵
    0.06
     Tyr
    0.06
     ）↵
    0.06
    صب
    0.06
    _,↵
    0.06
    >;↵↵
    0.06
    "];
↵
    0.06
    Act Density 0.000%

    No Known Activations