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

    Neuronpedia

    INDEX
    Explanations

    city population

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᕋ
    0.37
     अदिति
    0.34
    หย
    0.33
     வைத்து
    0.32
    堂
    0.31
     buccal
    0.31
    ल्लभ
    0.31
    ლებელია
    0.31
     প্রাসাদ
    0.30
     বিন্দু
    0.30
    POSITIVE LOGITS
    0.40
    0.39
     Rah
    0.36
     ホーム
    0.35
    0.34
     promozione
    0.34
    0.33
    കളും
    0.33
    0.33
                
    0.33
    Act Density 0.036%

    No Known Activations