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

    Neuronpedia

    INDEX
    Explanations

    prime numbers and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    owę
    1.09
    见的
    1.05
    ậ
    1.04
    itionally
    1.03
    ší
    1.02
     sự
    1.00
    ępnie
    0.98
     වලින්
    0.98
     androidTest
    0.96
     bị
    0.96
    POSITIVE LOGITS
    ర్
    1.02
    νει
    0.96
     inteiro
    0.95
    ות
    0.91
    a
    0.90
    tor
    0.89
    turning
    0.87
     scorsa
    0.86
    Mathemat
    0.85
     toque
    0.84
    Act Density 0.003%

    No Known Activations