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

    Neuronpedia

    INDEX
    Explanations

    baking soda, dish soap, Sofia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᠮ
    0.39
    ার্চ
    0.37
     حل
    0.35
    ঙ্গ
    0.34
    ন্টি
    0.34
    ార్థ
    0.33
    วล
    0.33
    듑
    0.33
    Мушко
    0.33
    شل
    0.33
    POSITIVE LOGITS
    ソ
    2.84
     Со
    2.80
     सो
    2.67
     ソ
    2.64
    索
    2.53
     소
    2.50
    SO
    2.45
    Со
    2.45
     సో
    2.42
     SO
    2.34
    Act Density 0.132%

    No Known Activations