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

    Neuronpedia

    INDEX
    Explanations

    sentence end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semua
    0.45
    جميع
    0.45
     erinn
    0.44
     zelfs
    0.43
     którzy
    0.42
    મ્પ
    0.42
     وكذلك
    0.41
     continuar
    0.41
     oraz
    0.41
     bahkan
    0.40
    POSITIVE LOGITS
     Usually
    0.70
     usually
    0.70
    它
    0.68
     সাধারণত
    0.68
     обычно
    0.68
     ብዙውን
    0.67
    бычно
    0.66
     typically
    0.66
    usually
    0.63
     Typically
    0.63
    Act Density 0.449%

    No Known Activations