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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions involving variables

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

    greatest common divisor or factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.47
     Feinde
    -0.42
     Sünde
    -0.39
    <?
    -0.39
     défend
    -0.38
     nemlig
    -0.34
     EconPapers
    -0.33
    etCode
    -0.32
    eriksaan
    -0.32
     vacun
    -0.32
    POSITIVE LOGITS
     ſind
    0.75
    دانشنامهٔ
    0.70
     ſei
    0.60
     فريبيس
    0.57
     ་་
    0.57
     zwiſchen
    0.56
    bcryptjs
    0.54
     Centurion
    0.54
    بوابة
    0.53
     $_(
    0.51
    Act Density 0.301%

    No Known Activations