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

    Neuronpedia

    INDEX
    Explanations

    conjunctions followed by explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    0.47
     máme
    0.46
     tenemos
    0.42
     kita
    0.41
    ’
    0.41
     n
    0.41
    ERO
    0.40
    ิ
    0.40
    ﺔ
    0.40
     máte
    0.40
    POSITIVE LOGITS
     thereby
    0.41
     inaccur
    0.40
     captivated
    0.40
    점에서
    0.40
     inextricably
    0.40
     troubled
    0.39
     narrowly
    0.39
     prompting
    0.39
     draped
    0.39
     noticeably
    0.38
    Act Density 0.942%

    No Known Activations