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

    Neuronpedia

    INDEX
    Explanations

    a followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.40
    ın
    0.37
     сегодняш
    0.37
     davranış
    0.36
     của
    0.35
     ilişkin
    0.34
     divulg
    0.34
     instaur
    0.34
     privind
    0.33
     değeri
    0.33
    POSITIVE LOGITS
    \
    0.37
    let
    0.31
    bl
    0.31
     ponds
    0.30
     you
    0.30
     lettuce
    0.29
     lagoons
    0.29
    ter
    0.29
    ert
    0.29
     water
    0.29
    Act Density 2.292%

    No Known Activations