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

    Neuronpedia

    INDEX
    Explanations

    splitting and dividing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মবার
    0.40
    嫨
    0.36
    趕
    0.34
    oer
    0.33
    ኘት
    0.33
     গম্ভীর
    0.33
    とな
    0.33
    を押
    0.33
    immung
    0.32
    )\|_{
    0.32
    POSITIVE LOGITS
     split
    3.41
    split
    3.09
     splitting
    3.02
    Split
    3.00
     Split
    3.00
     divided
    2.89
     splits
    2.88
    分割
    2.80
     разде
    2.72
     divide
    2.69
    Act Density 0.192%

    No Known Activations