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

    Neuronpedia

    INDEX
    Explanations

    centuries and historical periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.55
    osi
    0.44
    ：
    0.43
    iti
    0.43
    ong
    0.43
    اند
    0.43
    、
    0.42
    ions
    0.42
    ї
    0.42
    ди
    0.41
    POSITIVE LOGITS
    _
    0.54
    h
    0.49
    the
    0.46
    zeuge
    0.43
     Archa
    0.42
     Dabei
    0.41
    histoire
    0.41
     millennium
    0.41
     истории
    0.40
     historii
    0.40
    Act Density 0.443%

    No Known Activations