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

    Neuronpedia

    INDEX
    Explanations

    usability principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    装修
    0.46
    ほうが
    0.42
    贼
    0.39
    ování
    0.38
    トーク
    0.37
    şiv
    0.37
     উপমহাদেশের
    0.36
    कार्ट
    0.36
    茘
    0.36
     voire
    0.35
    POSITIVE LOGITS
    Systems
    0.42
    Allow
    0.39
    ('.')
    0.36
    Alliance
    0.36
    Display
    0.35
     Display
    0.35
    ')));
    0.35
    Dana
    0.35
     उद्यमियों
    0.35
     Ferdinand
    0.34
    Act Density 0.001%

    No Known Activations