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

    Neuronpedia

    INDEX
    Explanations

    often the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    телите
    0.48
    orit
    0.46
    recated
    0.45
    already
    0.44
    inflammation
    0.43
    เก่า
    0.43
     deri
    0.43
     saurait
    0.42
    RECENT
    0.42
    spiration
    0.40
    POSITIVE LOGITS
     Perché
    0.49
     γιατί
    0.48
    范
    0.48
     ადამიან
    0.47
     Tir
    0.47
     Enseñ
    0.45
     ಸೆ
    0.43
     Sé
    0.43
    Sé
    0.43
     অর্থে
    0.43
    Act Density 0.002%

    No Known Activations