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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уточ
    -0.07
     Họ
    -0.07
     deficits
    -0.06
     비교
    -0.06
    =============
    -0.06
     predator
    -0.06
     Establishment
    -0.06
    iscing
    -0.06
    컬
    -0.06
    by
    -0.06
    POSITIVE LOGITS
    πι
    0.08
    :variables
    0.06
    인이
    0.06
     afar
    0.06
     shower
    0.06
     получить
    0.06
    -stats
    0.06
    ήν
    0.06
    bgcolor
    0.06
     Without
    0.06
    Act Density 0.004%

    No Known Activations