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

    Neuronpedia

    INDEX
    Explanations

    ellipses and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ୧
    0.42
    FFF
    0.40
     îmb
    0.39
    ាញ
    0.39
     нако
    0.38
    𒋾
    0.38
     Kuk
    0.37
    bullets
    0.37
    ແມ
    0.36
    Fang
    0.36
    POSITIVE LOGITS
     ."
    0.55
     .'
    0.48
     .(
    0.44
     .
    0.44
     [.
    0.42
     .$
    0.41
     '[
    0.40
     .{
    0.39
    িত্ব
    0.38
     [+]
    0.38
    Act Density 0.001%

    No Known Activations