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

    Neuronpedia

    INDEX
    Explanations

    customer needs request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turning
    0.40
    transformation
    0.40
     smell
    0.40
     Zweiten
    0.40
     enjoy
    0.39
     Transforming
    0.39
     transformed
    0.39
     enjoying
    0.39
    越來越
    0.38
     humidity
    0.38
    POSITIVE LOGITS
     כל
    0.47
    ۵
    0.42
     пожалуйста
    0.42
    Capabilities
    0.42
    Ⅰ
    0.41
     capabilities
    0.41
    ✿
    0.41
    onCreate
    0.41
    0.41
     کل
    0.41
    Act Density 0.001%

    No Known Activations