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

    Neuronpedia

    INDEX
    Explanations

    towards others or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    man
    1.01
     counterpart
    0.99
    U
    0.97
    ‌ನ
    0.96
    ched
    0.90
     tenant
    0.88
     hạt
    0.87
     quartet
    0.87
    ภาค
    0.86
    一名
    0.86
    POSITIVE LOGITS
     Their
    1.17
     egos
    1.17
    他们的
    1.15
     അവരുടെ
    1.13
    他們的
    1.12
    纷纷
    1.10
     Productivity
    1.09
     რომლებიც
    1.09
    তারা
    1.08
     jų
    1.07
    Act Density 0.547%

    No Known Activations