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

    Neuronpedia

    INDEX
    Explanations

    describing concepts with follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قبول
    0.48
     مخصوص
    0.46
    ùm
    0.46
    ərb
    0.46
    ۔
    0.46
     کشور
    0.46
    ‌ನಲ್ಲಿ
    0.45
     වැඩ
    0.45
    ATION
    0.44
    atsiooni
    0.44
    POSITIVE LOGITS
     is
    0.50
     Mig
    0.50
     Mas
    0.46
     are
    0.46
     Mant
    0.44
     arbre
    0.44
    尊
    0.43
     mante
    0.42
     sont
    0.42
     আগ
    0.41
    Act Density 0.000%

    No Known Activations