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

    Neuronpedia

    INDEX
    Explanations

    listspointeachothername

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইউএন
    1.23
     检测
    1.23
    𝗮
    1.20
    নেস
    1.18
     infrared
    1.17
    可以是
    1.17
     strobe
    1.17
    чита
    1.14
     darn
    1.14
     Benfica
    1.13
    POSITIVE LOGITS
    he
    1.19
     *.
    1.08
    Раз
    1.05
    न्व
    1.04
     secession
    1.03
    ر
    1.02
     drawers
    1.01
     देण्यात
    1.00
    wider
    0.98
    django
    0.97
    Act Density 0.001%

    No Known Activations