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

    Neuronpedia

    INDEX
    Explanations

    keywords and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    regel
    0.42
     antifreeze
    0.39
     صفر
    0.38
     furnaces
    0.38
     glassware
    0.38
     intravenous
    0.37
     خطوات
    0.37
    hav
    0.37
     monolayers
    0.37
    FAF
    0.37
    POSITIVE LOGITS
     keywords
    1.03
    keywords
    0.97
     tags
    0.96
     Tags
    0.89
    Tags
    0.87
     keyword
    0.87
     Keywords
    0.86
    Keywords
    0.84
    tags
    0.84
    タグ
    0.83
    Act Density 0.190%

    No Known Activations