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

    Neuronpedia

    INDEX
    Explanations

    headings and bold text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سلاټ
    0.32
    𠄌
    0.32
     fuzzy
    0.31
     blurry
    0.31
     cohomology
    0.30
     morphology
    0.29
     Euclidean
    0.29
     ontology
    0.29
     blobs
    0.29
     surjective
    0.29
    POSITIVE LOGITS
    </strong>
    0.41
    :
    0.38
     feme
    0.37
    Những
    0.35
     CLIENTI
    0.35
    </u>
    0.34
    ça
    0.34
    *:
    0.34
     Loại
    0.34
     première
    0.33
    Act Density 0.000%

    No Known Activations