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

    Neuronpedia

    INDEX
    Explanations

    punctuation and emoticons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असल्याने
    0.62
    でしたが
    0.58
     теркәлүсез
    0.57
    ...",
    0.55
    …).
    0.55
    ですので
    0.54
     इसलिये
    0.54
    きましたが
    0.54
    ありますが
    0.54
     असून
    0.53
    POSITIVE LOGITS
    ↵↵↵↵
    1.43
    ↵↵↵↵↵
    1.37
    ↵↵↵
    1.32
    ↵↵↵↵↵↵
    1.10
    ↵↵↵↵↵↵↵
    1.06
     :)
    1.03
    ↵↵↵↵↵↵↵↵
    1.02
     Also
    0.98
     😊
    0.98
    ↵↵↵↵↵↵↵↵↵↵
    0.97
    Act Density 0.555%

    No Known Activations