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

    Neuronpedia

    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    2.41
    .,
    2.40
    ,[
    2.38
    !,
    2.34
     ,
    2.32
    *,
    2.30
     ،
    2.27
    (),
    2.27
    **,
    2.25
    +,
    2.20
    POSITIVE LOGITS
    តែ
    0.83
    ቹ
    0.70
     উভয়
    0.65
    ቹን
    0.60
    othed
    0.58
     selben
    0.58
     కాని
    0.58
    ારીખ
    0.58
     Wikiseite
    0.57
    jaty
    0.57
    Act Density 1.202%

    No Known Activations