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

    Neuronpedia

    INDEX
    Explanations

    reading files and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mara
    0.41
     клини
    0.40
    โน
    0.40
    abek
    0.40
    lifestyle
    0.39
    เปลี่ยน
    0.39
     Clown
    0.38
     ശബരിമല
    0.37
    Ross
    0.37
    antikan
    0.37
    POSITIVE LOGITS
    读取
    1.00
     读取
    0.96
     StreamReader
    0.94
     lettura
    0.88
     reading
    0.85
     read
    0.84
     Reads
    0.83
     читать
    0.82
     reads
    0.80
    readFile
    0.80
    Act Density 0.456%

    No Known Activations