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

    Neuronpedia

    INDEX
    Explanations

    complex, argumentative writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDE
    -0.06
    Separated
    -0.06
     누구
    -0.06
    .writeln
    -0.06
    (fixture
    -0.06
     nutzen
    -0.06
    ﾝ
    -0.06
     Polar
    -0.06
     adicion
    -0.06
    .release
    -0.06
    POSITIVE LOGITS
     plutôt
    0.07
     juste
    0.06
    _BITMAP
    0.06
    аблиц
    0.06
    ................................................................
    0.06
    够
    0.06
    278
    0.06
    ................
    0.06
     disag
    0.06
     financially
    0.06
    Act Density 0.094%

    No Known Activations