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

    Neuronpedia

    INDEX
    Explanations

    education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ков
    0.61
    认为
    0.56
    خ
    0.56
     რა
    0.54
     Dier
    0.54
    似乎
    0.52
    是要
    0.51
    ਡ
    0.50
     ਹ
    0.50
     기존
    0.50
    POSITIVE LOGITS
    ate
    0.61
     estudios
    0.59
    ih
    0.56
    id
    0.56
    iation
    0.55
    able
    0.55
    ik
    0.55
    ال
    0.55
    ala
    0.55
    oras
    0.54
    Act Density 0.013%

    No Known Activations