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

    Neuronpedia

    INDEX
    Explanations

    ending punctuation or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     όσο
    0.41
    ABILITY
    0.33
     Chees
    0.33
    IVEN
    0.32
     currentTime
    0.32
    葯
    0.32
     që
    0.31
    ถ้า
    0.30
    在我们
    0.30
     Annie
    0.30
    POSITIVE LOGITS
    。
    0.47
     alebo
    0.45
     veya
    0.45
    ।.
    0.45
    +.
    0.44
    trimenti
    0.44
    ។
    0.43
    ®.
    0.42
    otherwise
    0.42
     otherwise
    0.41
    Act Density 0.237%

    No Known Activations