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

    Neuronpedia

    INDEX
    Explanations

    columns, matrix, from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meerdere
    0.40
     mismo
    0.40
     Hewlett
    0.40
     fim
    0.38
     High
    0.38
     fairly
    0.38
     संभावना
    0.37
     रखें
    0.37
     tramite
    0.37
     জরিমানা
    0.37
    POSITIVE LOGITS
    ‌ترین
    0.44
    вест
    0.43
     अपनाने
    0.43
    мов
    0.42
     назвать
    0.42
    телей
    0.42
    óloga
    0.42
    प्पी
    0.42
    бить
    0.41
    𒅴
    0.41
    Act Density 0.016%

    No Known Activations