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

    Neuronpedia

    INDEX
    Explanations

    from a / of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पीड
    0.47
    romatic
    0.45
     टिकट
    0.43
    ストン
    0.41
     životu
    0.41
     zoveel
    0.41
    ୀ
    0.41
     dreaded
    0.41
    ztat
    0.40
    Seat
    0.39
    POSITIVE LOGITS
     BH
    0.48
     Bj
    0.47
     BJ
    0.40
     Rain
    0.40
     Vivi
    0.40
    م
    0.40
    بح
    0.39
     BBS
    0.39
     DH
    0.39
     Viv
    0.39
    Act Density 0.000%

    No Known Activations