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

    Neuronpedia

    INDEX
    Explanations

    technical, factual, definitions, foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াল
    0.47
     verwend
    0.45
    ો
    0.45
    ت
    0.41
    odni
    0.40
    ോ
    0.40
     Nasir
    0.39
    ص
    0.38
     Ayurved
    0.38
    liel
    0.38
    POSITIVE LOGITS
     recuperação
    0.53
    発電
    0.49
    électricité
    0.47
    Geschichte
    0.45
    ያንዳ
    0.45
    㐬
    0.44
     চট্ট
    0.44
    getTransaction
    0.43
    класс
    0.43
    电动
    0.43
    Act Density 0.003%

    No Known Activations