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

    Neuronpedia

    INDEX
    Explanations

    environmental impact and sustainability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يا
    0.36
     αλλά
    0.31
     ως
    0.31
     άνθρω
    0.29
    ного
    0.29
    اں
    0.29
     жи
    0.29
    وم
    0.28
     Пор
    0.28
     as
    0.28
    POSITIVE LOGITS
    }\
    0.36
    IN
    0.36
    }
    0.35
    })$
    0.34
    ad
    0.34
    <0x80>
    0.34
     Recycle
    0.33
     Recycling
    0.33
    recycl
    0.33
    釭
    0.32
    Act Density 0.053%

    No Known Activations