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

    Neuronpedia

    INDEX
    Explanations

    noun suffixes and compound nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    СТ
    0.52
    꺅
    0.51
     অন্য
    0.49
    ளைஞ
    0.49
     wichtigen
    0.49
     прибыль
    0.49
    ழந்த
    0.49
     μεγ
    0.48
    सीना
    0.47
     आइट
    0.46
    POSITIVE LOGITS
    in
    0.62
    on
    0.61
     In
    0.60
    an
    0.59
    et
    0.59
    urator
    0.57
     A
    0.56
     I
    0.56
    ™
    0.55
    Manager
    0.55
    Act Density 0.021%

    No Known Activations