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

    Neuronpedia

    INDEX
    Explanations

    mentions of a deficiency or absence of something

    oai_token-act-pair · gemini-2.0-flash

    lack

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lack
    -0.63
     seulement
    -0.56
    lack
    -0.56
    Lack
    -0.52
    gnore
    -0.51
     lack
    -0.50
     Mangel
    -0.43
    бло
    -0.43
    '}
    -0.43
     Only
    -0.41
    POSITIVE LOGITS
    welli
    0.69
     Normdatei
    0.68
     تانيه
    0.68
    ็จ
    0.68
     незавершена
    0.64
     ویکی‌پدیا
    0.63
    alogical
    0.63
    urance
    0.63
    RectangleBorder
    0.63
     فريبيس
    0.61
    Act Density 3.866%

    No Known Activations