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

    Neuronpedia

    INDEX
    Explanations

    improved, start, get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.61
    b
    0.47
    7
    0.46
     is
    0.44
     Topical
    0.43
    [
    0.43
     Northern
    0.42
    రిత్ర
    0.42
     library
    0.42
    <
    0.40
    POSITIVE LOGITS
    ેચ્છ
    0.55
     zejména
    0.53
    ěk
    0.53
     укра
    0.52
    觓
    0.51
     κατά
    0.51
     arrivée
    0.50
     получится
    0.50
    hitva
    0.50
    tevõ
    0.49
    Act Density 0.002%

    No Known Activations