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

    Neuronpedia

    INDEX
    Explanations

    programming code and mathematical numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.55
    त
    0.51
    I
    0.48
    গ
    0.46
    و
    0.45
    वुड
    0.44
    B
    0.43
    우
    0.42
    st
    0.42
    wood
    0.42
    POSITIVE LOGITS
    faktor
    0.53
     fakt
    0.47
    ഓം
    0.46
     обслу
    0.46
     തിരിച്ച
    0.44
     kurie
    0.44
     કરે
    0.43
     funzionamento
    0.43
     berakhir
    0.43
     yě
    0.43
    Act Density 0.002%

    No Known Activations