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

    Neuronpedia

    INDEX
    Explanations

    OAuth 2.0 authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ដែល
    0.64
     лечения
    0.60
     జమ
    0.59
     أصبح
    0.57
    تي
    0.55
     शर्तों
    0.55
     것이
    0.54
     ఒకటి
    0.54
     하는데
    0.54
     الأمريكية
    0.53
    POSITIVE LOGITS
    :
    0.62
    ן
    0.59
     for
    0.58
    openc
    0.57
    ia
    0.56
     from
    0.55
     intercepted
    0.55
     revis
    0.54
    SMITH
    0.54
    ).
    0.54
    Act Density 0.003%

    No Known Activations