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

    Neuronpedia

    INDEX
    Explanations

    search engines and plugins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.12
    '
    1.07
    ان
    0.94
    ：
    0.91
    مار
    0.88
    م
    0.84
    مع
    0.84
    取材
    0.82
    iem
    0.81
    ร
    0.80
    POSITIVE LOGITS
    ти
    1.06
    ви
    1.03
    ות
    0.98
    تي
    0.97
    ية
    0.93
    п
    0.85
    ла
    0.78
    нта
    0.77
    ותו
    0.77
    ровать
    0.76
    Act Density 0.035%

    No Known Activations