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

    Neuronpedia

    INDEX
    Explanations

    Saying or mentioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arz
    -0.09
     incomparable
    -0.09
     Superior
    -0.08
     worthless
    -0.08
     қорға
    -0.08
     superior
    -0.07
     뛰
    -0.07
     превос
    -0.07
     заслуж
    -0.07
     merece
    -0.07
    POSITIVE LOGITS
     explicitly
    0.10
    లేదు
    0.10
    igeze
    0.10
     whatsoever
    0.09
     bislang
    0.09
    வில்லை
    0.09
     никаких
    0.09
     żad
    0.09
     سوى
    0.09
     sequer
    0.09
    Act Density 0.182%

    No Known Activations