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

    Neuronpedia

    INDEX
    Explanations

    multilingual or abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    પૂર્ણ
    1.21
    Surely
    1.20
     throats
    1.20
     injustices
    1.15
     garçon
    1.12
     floods
    1.12
    চিত্রে
    1.12
     herring
    1.10
     hairs
    1.09
     यूँ
    1.08
    POSITIVE LOGITS
    ться
    1.35
    seite
    1.20
    जग
    1.13
    ン
    1.10
    케
    1.03
    자리
    1.02
     Harmonic
    1.02
    ست
    1.00
     वहीं
    0.99
     Bayesian
    0.98
    Act Density 0.000%

    No Known Activations