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

    Neuronpedia

    INDEX
    Explanations

    generating value or profit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ictionary
    0.41
    ጋ
    0.41
    γγρα
    0.39
     ruptura
    0.39
     응
    0.38
    ائق
    0.38
    ANCED
    0.38
    ibration
    0.38
    Modeling
    0.37
    Transformation
    0.37
    POSITIVE LOGITS
     generating
    1.23
     приносит
    1.22
     generate
    1.21
     generates
    1.20
    generate
    1.09
    generating
    1.08
     yielding
    1.07
     Generating
    1.05
    带来
    1.04
     Generate
    1.01
    Act Density 0.020%

    No Known Activations