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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of specific Arabic characters and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Qaf and Qaysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    marvin
    -0.45
     Fernandez
    -0.45
    évaluateur
    -0.45
     Twin
    -0.44
    TestingModule
    -0.44
     sven
    -0.44
     inso
    -0.41
    บัน
    -0.41
     Elf
    -0.41
    تقاوى
    -0.40
    POSITIVE LOGITS
     ق
    1.46
     الق
    1.44
    ق
    1.23
    الق
    0.98
     q
    0.88
     للق
    0.88
    q
    0.87
     والق
    0.82
    Q
    0.78
     Q
    0.74
    Act Density 0.002%

    No Known Activations