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

    Neuronpedia

    INDEX
    Explanations

    speak Portuguese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.85
    ays
    0.81
    is
    0.75
    اب
    0.70
    a
    0.68
    ف
    0.65
    el
    0.65
    b
    0.64
    å
    0.63
    arthen
    0.61
    POSITIVE LOGITS
     স্প
    0.77
     spn
    0.69
     sp
    0.68
    。
    0.66
     Sp
    0.64
    灑
    0.64
    Sp
    0.63
     स्प
    0.63
     SP
    0.62
     commencer
    0.62
    Act Density 0.307%

    No Known Activations