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

    Neuronpedia

    INDEX
    Explanations

    stream reader writer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    outFile
    0.42
     легче
    0.41
     電力
    0.40
     eficaz
    0.39
     الملف
    0.39
    élect
    0.38
    MenuActive
    0.38
    鼓勵
    0.38
     செயல்
    0.38
    шений
    0.37
    POSITIVE LOGITS
    Reader
    0.58
    ToProps
    0.49
     Reader
    0.46
     reader
    0.44
     Portland
    0.44
     inputStream
    0.43
    Portland
    0.43
     Restoration
    0.41
     PT
    0.40
    Press
    0.40
    Act Density 0.003%

    No Known Activations