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

    Neuronpedia

    INDEX
    Explanations

    live streaming video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    痙
    0.42
     оптими
    0.41
     недель
    0.41
    一个月
    0.41
     чуде
    0.40
    ું
    0.40
    ModelGrid
    0.39
    たっぷり
    0.39
    成り
    0.39
    设有
    0.39
    POSITIVE LOGITS
    ho
    0.40
    was
    0.36
     한다
    0.36
    be
    0.35
    idian
    0.35
    redit
    0.35
     해도
    0.35
    aler
    0.34
    iman
    0.34
     Nave
    0.34
    Act Density 0.001%

    No Known Activations