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

    Neuronpedia

    INDEX
    Explanations

    ranging in tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нні
    0.47
    னால்
    0.43
    𝘆
    0.43
    нути
    0.42
    IER
    0.41
     акча
    0.41
    тон
    0.40
    制度
    0.40
    站在
    0.40
    𝑙
    0.40
    POSITIVE LOGITS
     cauliflower
    0.54
     fantastical
    0.50
     imaginative
    0.47
     joyful
    0.47
    ografi
    0.46
     evocative
    0.46
     ingl
    0.46
     intriguing
    0.46
     europäischen
    0.46
     fascinating
    0.44
    Act Density 0.013%

    No Known Activations