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

    Neuronpedia

    INDEX
    Explanations

    upselling, upskilling, up-to-date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്വം
    0.84
     कृत
    0.84
     MAM
    0.84
    ‍♂️
    0.83
    eria
    0.82
     upright
    0.80
     protr
    0.80
     {\
    0.80
    ەم
    0.79
    era
    0.78
    POSITIVE LOGITS
    GRADE
    1.51
    graded
    1.43
    welling
    1.43
    votes
    1.33
    grades
    1.32
    wards
    1.30
    rooted
    1.27
    stairs
    1.26
     gradation
    1.25
    COMING
    1.24
    Act Density 0.171%

    No Known Activations