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

    Neuronpedia

    INDEX
    Explanations

    Medical side effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     വരുന്ന
    -0.08
     vanaf
    -0.08
     olev
    -0.08
    的平台
    -0.07
     vanuit
    -0.07
     prv
    -0.07
     perfekt
    -0.07
    "B
    -0.07
    -0.07
    ，也是
    -0.07
    POSITIVE LOGITS
     unintended
    0.10
     inadvert
    0.10
     inadvertently
    0.09
     decreased
    0.09
     повыш
    0.09
     increased
    0.09
     некотор
    0.09
     aumentado
    0.09
     möglicherweise
    0.09
     снижение
    0.09
    Act Density 0.035%
    No Known Activations