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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وى
    -0.07
     sibling
    -0.07
     recipient
    -0.07
    �
    -0.06
     sca
    -0.06
     терап
    -0.06
    (cache
    -0.06
     benefited
    -0.06
     processor
    -0.06
     sigma
    -0.06
    POSITIVE LOGITS
     Orn
    0.08
    .BatchNorm
    0.07
    toLowerCase
    0.06
     YEARS
    0.06
     یاد
    0.06
    _Game
    0.06
    _LOOP
    0.06
     düşür
    0.06
    KL
    0.06
    ptions
    0.06
    Act Density 0.002%

    No Known Activations