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

    Neuronpedia

    INDEX
    Explanations

    definitions, descriptions, or offerings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qīng
    0.51
    خاب
    0.46
     complainant
    0.46
     auth
    0.45
     usurp
    0.45
     monomials
    0.44
     cookies
    0.44
     captions
    0.44
     pravil
    0.44
     cake
    0.44
    POSITIVE LOGITS
     अच्छी
    0.53
    ende
    0.52
    adeso
    0.51
     Strain
    0.48
    esperienza
    0.48
     Enjoy
    0.47
     농
    0.47
    ia
    0.46
    encounter
    0.46
    iad
    0.46
    Act Density 0.002%

    No Known Activations