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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ходить
    -0.06
     делать
    -0.06
     الولايات
    -0.06
     Loved
    -0.06
     demek
    -0.06
    ходит
    -0.06
     Liz
    -0.06
     говор
    -0.06
     diving
    -0.06
    (no
    -0.06
    POSITIVE LOGITS
     обов
    0.07
     rehears
    0.06
     transported
    0.06
     bere
    0.06
     commerce
    0.06
     WF
    0.06
    .security
    0.06
    .nn
    0.06
    ":-
    0.06
     primaryStage
    0.06
    Act Density 0.031%

    No Known Activations