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

    Neuronpedia

    INDEX
    Explanations

    macros and modern concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.70
    ك
    0.65
    ل
    0.64
    ين
    0.54
    ด
    0.53
    ير
    0.52
    기
    0.51
    스
    0.51
    จะ
    0.50
    ל
    0.50
    POSITIVE LOGITS
     밝혔
    0.50
    0
    0.48
    <0x80>
    0.46
    fifth
    0.46
    fiction
    0.42
     for
    0.40
    ible
    0.40
     in
    0.39
    for
    0.39
    informatics
    0.39
    Act Density 0.001%

    No Known Activations