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

    Neuronpedia

    INDEX
    Explanations

    update

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commenced
    -0.07
     areas
    -0.06
     devices
    -0.06
     compound
    -0.06
     cooking
    -0.06
    _bases
    -0.06
     payments
    -0.06
    Bounds
    -0.06
     homes
    -0.06
     capability
    -0.06
    POSITIVE LOGITS
    ğim
    0.07
    áo
    0.07
     котор
    0.06
     battered
    0.06
    컵
    0.06
     инструмент
    0.06
     فق
    0.06
     нему
    0.06
    preload
    0.06
    méně
    0.06
    Act Density 0.004%

    No Known Activations