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

    Neuronpedia

    INDEX
    Explanations

    character descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మరింత
    0.47
     ಮಾಹಿತಿ
    0.45
     விரைவில்
    0.42
     Garant
    0.40
    !";
    0.40
     garant
    0.39
     ವಿವರ
    0.39
     РФ
    0.39
     garantire
    0.39
     রহিয়াছে
    0.38
    POSITIVE LOGITS
    。
    0.55
    ।
    0.44
    .
    0.41
     communists
    0.40
     angry
    0.39
     funerals
    0.39
     。
    0.38
     गुस्सा
    0.38
    ــــــــ
    0.37
     asshole
    0.37
    Act Density 0.036%

    No Known Activations