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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nécessité
    0.50
    0.49
    benhav
    0.47
     frivolous
    0.47
     bekl
    0.44
     be
    0.44
    ेंद्रीय
    0.42
     viktigt
    0.42
     hyg
    0.42
     acontece
    0.41
    POSITIVE LOGITS
    +(
    0.46
    த்தின்
    0.46
     اپنے
    0.45
    Helper
    0.44
     !=
    0.42
    上記
    0.42
     ওয়ালপেপার
    0.41
    GetName
    0.40
     اپنی
    0.40
    の
    0.40
    Act Density 0.316%

    No Known Activations