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

    Neuronpedia

    INDEX
    Explanations

    Singular, Chorus, Gender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ದು
    0.54
     जब
    0.50
     চাহিয়া
    0.50
     Fitting
    0.49
     جع
    0.47
     सही
    0.47
     চাহিল
    0.46
     ಕೂ
    0.46
     Negotiations
    0.46
     Satu
    0.45
    POSITIVE LOGITS
    :
    0.61
    h
    0.55
    ilité
    0.49
     distillate
    0.48
    n
    0.47
    *
    0.47
    mig
    0.47
    m
    0.46
    a
    0.45
    p
    0.45
    Act Density 0.001%

    No Known Activations