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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values or quantities

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

    two or second

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.68
    躇
    -0.66
     ویکی‌پدی
    -0.61
    msgTypes
    -0.59
    avelength
    -0.58
    فایل‌لار
    -0.57
    olyb
    -0.57
    ंदीखरीदारी
    -0.57
     informée
    -0.57
    tangentMode
    -0.57
    POSITIVE LOGITS
    二
    1.75
     二
    1.30
     second
    0.93
     two
    0.86
     Second
    0.79
     Two
    0.73
    Second
    0.70
     seconde
    0.69
    second
    0.69
     SECOND
    0.68
    Act Density 0.002%

    No Known Activations