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

    Neuronpedia

    INDEX
    Explanations

    Star Wars expanded universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.31
    it
    1.00
    ي
    0.96
    on
    0.88
    l
    0.86
    F
    0.85
    al
    0.84
    u
    0.84
    ol
    0.84
    و
    0.80
    POSITIVE LOGITS
    ים
    0.75
    ید
    0.72
     emailing
    0.66
     Skywalker
    0.66
     acheté
    0.64
    ě
    0.63
     ড
    0.63
    ähler
    0.63
     étrang
    0.61
     Darth
    0.61
    Act Density 0.003%

    No Known Activations