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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цер
    -0.07
    aurant
    -0.06
    UserController
    -0.06
     Trek
    -0.06
     chtěl
    -0.06
     �
    -0.06
    τεύ
    -0.06
     oasis
    -0.06
    .softmax
    -0.06
    .ReadAsStringAsync
    -0.06
    POSITIVE LOGITS
     familia
    0.07
     At
    0.07
     Hud
    0.07
     bets
    0.06
     government
    0.06
     aiding
    0.06
     redund
    0.06
    -season
    0.06
    請
    0.06
     Famous
    0.06
    Act Density 0.000%

    No Known Activations