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

    Neuronpedia

    INDEX
    Explanations

    string splitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الكتاب
    0.43
    onycha
    0.40
     किताब
    0.38
     zusätzlich
    0.38
    Succ
    0.37
     tillegg
    0.36
     chant
    0.35
     اجر
    0.35
     książ
    0.35
    Book
    0.34
    POSITIVE LOGITS
     split
    1.88
    split
    1.80
     Split
    1.71
    Split
    1.66
     splitting
    1.66
     splits
    1.62
    splits
    1.45
     Splits
    1.44
    splitted
    1.40
     splitter
    1.37
    Act Density 0.048%

    No Known Activations