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

    Neuronpedia

    INDEX
    Explanations

    We followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    реа
    0.41
     ڈپاز
    0.40
    प्ले
    0.40
    橑
    0.40
     Trouvez
    0.40
    遄
    0.39
     кожен
    0.38
    入門
    0.37
     każdy
    0.37
     типа
    0.36
    POSITIVE LOGITS
    nesday
    0.61
    ierstrass
    0.57
    bsite
    0.54
    bley
    0.52
     weir
    0.52
    eping
    0.51
    hrmacht
    0.50
    ighed
    0.50
     Weimar
    0.49
     WE
    0.48
    Act Density 0.012%

    No Known Activations