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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只能
    -0.07
    car
    -0.07
    cou
    -0.07
     Augusta
    -0.06
    -large
    -0.06
     Roll
    -0.06
     sturdy
    -0.06
    azaar
    -0.06
    Chair
    -0.06
     dop
    -0.06
    POSITIVE LOGITS
     ESL
    0.07
    oví
    0.06
     athe
    0.06
     اک
    0.06
     เพราะ
    0.06
     een
    0.06
     Allah
    0.06
     einer
    0.06
     Goku
    0.06
    0.06
    Act Density 0.000%

    No Known Activations