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

    Neuronpedia

    INDEX
    Explanations

    lists and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hat
    0.79
    集團
    0.76
    ato
    0.73
    kelijk
    0.73
    лой
    0.70
    力が
    0.70
    <bos>
    0.69
    zenes
    0.69
    }+(
    0.68
    acht
    0.68
    POSITIVE LOGITS
     items
    1.21
     Items
    1.17
    ভুক্ত
    1.14
     Compiled
    1.12
     contents
    1.10
     vitamins
    1.04
     Vitamins
    1.03
     Item
    1.03
    Items
    1.01
     compiled
    1.01
    Act Density 1.154%

    No Known Activations