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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temporary
    -0.07
    .primary
    -0.07
     yür
    -0.07
     Yunan
    -0.07
     SSC
    -0.07
    -door
    -0.06
     υπηρε
    -0.06
     waiting
    -0.06
     Porter
    -0.06
     Byz
    -0.06
    POSITIVE LOGITS
     good
    0.09
     จำนวน
    0.06
    opsy
    0.06
     вас
    0.06
    Swift
    0.06
    ’é
    0.06
     meal
    0.06
     Essen
    0.06
     particularly
    0.06
     Gow
    0.06
    Act Density 0.022%

    No Known Activations