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

    Neuronpedia

    INDEX
    Explanations

    false positive, independence, high quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     खातों
    0.47
    чности
    0.43
    セプト
    0.42
     આગાહી
    0.41
     वर्णन
    0.41
     кожи
    0.41
     провод
    0.40
    恐怕
    0.40
    ৌর
    0.40
    年は
    0.40
    POSITIVE LOGITS
    Zo
    0.40
     rik
    0.38
    റും
    0.37
    Schneider
    0.37
    Pen
    0.37
     Kef
    0.36
     pen
    0.35
     route
    0.35
     Sinclair
    0.34
    ﻁ
    0.34
    Act Density 0.001%

    No Known Activations