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

    Neuronpedia

    INDEX
    Explanations

    small simple quiet romantic core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     немає
    0.54
     unsere
    0.52
    都不是
    0.50
     esclus
    0.48
     hunting
    0.47
     Disponible
    0.46
     Zustand
    0.46
     eint
    0.46
     எல்லா
    0.45
     yelling
    0.45
    POSITIVE LOGITS
     (
    0.51
    (
    0.50
    co
    0.46
    O
    0.46
    oju
    0.44
    ji
    0.42
     +
    0.42
    subfloat
    0.40
    con
    0.40
    šel
    0.40
    Act Density 0.003%

    No Known Activations