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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dens
    -0.08
    arters
    -0.07
    χό
    -0.07
     Mobil
    -0.07
     applaud
    -0.07
    223
    -0.06
     beau
    -0.06
     square
    -0.06
     Hammond
    -0.06
    omaly
    -0.06
    POSITIVE LOGITS
     twice
    0.07
     zaw
    0.06
     strikes
    0.06
     eCommerce
    0.06
    .trim
    0.06
    Newsletter
    0.06
     přízn
    0.06
     ldb
    0.06
     fortunately
    0.06
     �
    0.05
    Act Density 0.003%

    No Known Activations