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

    Neuronpedia

    INDEX
    Explanations

    expansion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Org
    -0.08
    FRAME
    -0.08
     bumps
    -0.07
     costo
    -0.07
     homes
    -0.07
    朦
    -0.07
    ☢
    -0.07
     дом
    -0.07
    snow
    -0.07
    odom
    -0.07
    POSITIVE LOGITS
    imize
    0.07
    را
    0.07
    做大做强
    0.07
    าก
    0.07
     raise
    0.07
    據
    0.07
    AB
    0.07
     done
    0.07
     FROM
    0.07
    打破
    0.07
    Act Density 0.004%

    No Known Activations