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

    Neuronpedia

    INDEX
    Explanations

    sentence endings, polite verbs。

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    andom
    0.70
     exacerbated
    0.63
    +,
    0.61
     [,
    0.60
     wise
    0.59
    ercise
    0.54
    چی
    0.54
     +,
    0.54
    !,
    0.53
     AKA
    0.52
    POSITIVE LOGITS
    。
    1.96
    。「
    1.50
    。"
    1.48
    。(
    1.47
    。.
    1.44
    。」
    1.44
    。\
    1.43
    。（
    1.42
    。",
    1.36
    。</
    1.33
    Act Density 0.004%

    No Known Activations