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

    Neuronpedia

    INDEX
    Explanations

    describing specific qualities or methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.46
     be
    0.42
     आने
    0.37
     appunto
    0.36
     Procedures
    0.35
     C
    0.35
     Acrylic
    0.34
     Immunology
    0.34
     .
    0.34
    တစ်
    0.34
    POSITIVE LOGITS
    ༠
    0.47
     yani
    0.47
    ᠲ
    0.46
    પણે
    0.45
    źć
    0.44
    стойчи
    0.44
    asının
    0.43
    เข้าใจ
    0.43
    тык
    0.42
     daca
    0.42
    Act Density 0.155%

    No Known Activations