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

    Neuronpedia

    INDEX
    Explanations

    descriptions of categories and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vitth
    0.40
    बित
    0.39
    Gotham
    0.39
    웁
    0.39
     আমি
    0.39
    म्ब
    0.38
     Öffentlich
    0.38
     केवल
    0.37
     ખૂબ
    0.37
    맨
    0.37
    POSITIVE LOGITS
    蒻
    0.40
     countries
    0.38
     diaspora
    0.37
     hosted
    0.36
     तम्
    0.36
    峨
    0.35
     身
    0.35
     populations
    0.35
     genders
    0.34
     pet
    0.34
    Act Density 0.000%

    No Known Activations