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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...",
    0.60
    ...,
    0.59
     development
    0.59
    ...',
    0.56
    ...),
    0.55
    -}$
    0.55
     targeted
    0.54
    -
    0.54
    されており
    0.52
     ...,
    0.52
    POSITIVE LOGITS
     😊
    1.35
     :)
    1.26
    😊
    1.17
     🙂
    1.13
     Goodbye
    1.05
     😁
    1.04
     😀
    1.02
    ☺️
    1.02
     😄
    1.00
     hehe
    1.00
    Act Density 0.150%

    No Known Activations