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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мереж
    -0.08
    foobar
    -0.07
     kos
    -0.07
     Arnold
    -0.06
     digits
    -0.06
     +-
    -0.06
    aptops
    -0.06
     Lumpur
    -0.06
     دقی
    -0.06
     бач
    -0.06
    POSITIVE LOGITS
    чают
    0.06
     orderId
    0.06
    ="_
    0.06
    ΥΣ
    0.06
    ούς
    0.06
     verv
    0.06
    ern
    0.06
     verir
    0.06
    追
    0.06
    buttonShape
    0.06
    Act Density 0.002%

    No Known Activations