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

    Neuronpedia

    INDEX
    Explanations

    yet, contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ្នក
    1.40
    quay
    1.26
    لای
    1.20
    ل
    1.14
    ar
    1.13
    رض
    1.13
    ក
    1.09
     hawk
    1.05
     licenciado
    1.05
    adays
    1.05
    POSITIVE LOGITS
    ้
    1.52
    𝚛
    1.47
    𝚙
    1.47
    но
    1.43
    ные
    1.40
    ного
    1.40
    री
    1.38
    𝚜
    1.38
    𝚑
    1.35
    िया
    1.34
    Act Density 0.001%

    No Known Activations