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

    Neuronpedia

    INDEX
    Explanations

    engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     клет
    -0.07
     tallest
    -0.07
     +%
    -0.06
     bekommen
    -0.06
     wiring
    -0.06
    악
    -0.06
    qty
    -0.06
     false
    -0.06
     krij
    -0.06
    toMatch
    -0.06
    POSITIVE LOGITS
     возраст
    0.07
    ()")↵
    0.07
    odor
    0.07
    روی
    0.06
    .EN
    0.06
    地區
    0.06
    ρκε
    0.06
    Few
    0.06
    ved
    0.06
     Inquiry
    0.06
    Act Density 0.014%

    No Known Activations