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

    Neuronpedia

    INDEX
    Explanations

    must critically analyze results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ელის
    0.45
     concetto
    0.44
    有料
    0.43
    実は
    0.43
    깎
    0.41
     ücret
    0.41
    腱
    0.41
     ikke
    0.41
    ။
    0.40
    চ্ছ
    0.40
    POSITIVE LOGITS
     باید
    0.50
     follows
    0.49
     devem
    0.48
     सर्वेक्षण
    0.47
     ময়মনসিংহ
    0.46
    Result
    0.46
     ይሰ
    0.45
     Hasil
    0.45
     doivent
    0.45
     seguintes
    0.44
    Act Density 0.004%

    No Known Activations