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

    Neuronpedia

    INDEX
    Explanations

    often

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soll
    -0.09
     tenth
    -0.08
     wobei
    -0.08
     fourteen
    -0.08
     sollen
    -0.08
     alimentation
    -0.08
     أربعة
    -0.08
     sacred
    -0.08
     asupra
    -0.08
     peab
    -0.07
    POSITIVE LOGITS
    不错
    0.11
     odlič
    0.10
     excelentes
    0.10
     offers
    0.10
     brukar
    0.09
     ót
    0.09
     offer
    0.09
     ofrecen
    0.09
     excellent
    0.09
     sûrement
    0.09
    Act Density 0.082%

    No Known Activations