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

    Neuronpedia

    INDEX
    Explanations

    words ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.50
     Comet
    0.49
     "
    0.46
    IDGE
    0.45
     white
    0.45
     ،
    0.44
     Social
    0.44
     talent
    0.44
     talon
    0.43
     negation
    0.42
    POSITIVE LOGITS
     ලබා
    0.50
    牍
    0.48
    FI
    0.48
     रखेंगे
    0.47
    获得的
    0.46
    Supplementary
    0.46
    `],
    0.45
     ተጨማሪ
    0.45
    ools
    0.44
     canaux
    0.44
    Act Density 0.003%

    No Known Activations