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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，所以
    -0.08
     그리고
    -0.08
    ière
    -0.08
     trif
    -0.08
     whose
    -0.08
    且
    -0.08
    tria
    -0.08
     macam
    -0.07
    iske
    -0.07
     antagonist
    -0.07
    POSITIVE LOGITS
     вариант
    0.10
     viable
    0.09
     allerdings
    0.09
     granul
    0.09
     eignet
    0.08
     것도
    0.08
     eignen
    0.08
     Brows
    0.08
     бесплат
    0.08
     However
    0.08
    Act Density 0.072%

    No Known Activations