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

    Neuronpedia

    INDEX
    Explanations

    test/qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    水电
    0.48
    н
    0.44
    addEnemy
    0.42
    ıyor
    0.41
    多么
    0.41
    кор
    0.39
    л
    0.39
     ஸ்
    0.39
     शर्ट
    0.39
     Shirts
    0.39
    POSITIVE LOGITS
    Czy
    0.51
    Mail
    0.47
    Swing
    0.46
     (=
    0.46
    ulates
    0.46
     terroir
    0.45
    Business
    0.45
     culminated
    0.45
     मालिनी
    0.44
    स्कृत
    0.44
    Act Density 0.000%

    No Known Activations