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

    Neuronpedia

    INDEX
    Explanations

    jokes, banker, doctor, year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     from
    0.52
    l
    0.51
     sphinct
    0.50
     tener
    0.49
     caramel
    0.49
    Duel
    0.49
     that
    0.48
    Self
    0.48
    ل
    0.47
    Colour
    0.47
    POSITIVE LOGITS
     ඔවුන්
    0.40
     జరిగిన
    0.40
     \%(
    0.39
     específicamente
    0.38
    甚至
    0.37
    ścia
    0.37
    lblCredits
    0.37
     පිළ
    0.36
     विषयों
    0.36
     오래
    0.36
    Act Density 0.006%

    No Known Activations