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

    Neuronpedia

    INDEX
    Explanations

    deeply personal, zIndex :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhiên
    1.08
    adamente
    1.07
    മായും
    1.05
    怛
    1.03
    ুদ্ধ
    1.01
     오
    1.01
     ضرورت
    0.98
    inicial
    0.98
     вдоль
    0.97
    isierte
    0.96
    POSITIVE LOGITS
     siden
    0.99
    cella
    0.98
     Phantom
    0.97
    Iron
    0.97
     Aniston
    0.96
    たた
    0.94
    களில்
    0.92
    茈
    0.92
     misses
    0.91
    น้อง
    0.91
    Act Density 0.001%

    No Known Activations