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

    Neuronpedia

    INDEX
    Explanations

    several types of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ہ
    0.59
    0.53
    н
    0.53
     Footage
    0.52
    是一个
    0.51
     an
    0.50
    an
    0.50
     uncertainty
    0.49
     Uncertainty
    0.49
     occupies
    0.48
    POSITIVE LOGITS
    ्स
    0.74
     различные
    0.65
    ्य
    0.63
     vários
    0.63
     dva
    0.59
     várias
    0.59
     duas
    0.58
    几种
    0.58
     notori
    0.57
     dvě
    0.57
    Act Density 0.003%

    No Known Activations