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

    Neuronpedia

    INDEX
    Explanations

    writing and plotting stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਿਆ
    0.42
     поэ
    0.40
    員工
    0.39
    ਡੀ
    0.38
     seconds
    0.37
    subjects
    0.37
    ̣t
    0.37
     pria
    0.36
    تميز
    0.36
    ܕ
    0.36
    POSITIVE LOGITS
    Outline
    0.55
    Pant
    0.53
     reread
    0.52
     querying
    0.52
     plotter
    0.51
    Query
    0.50
     manuscript
    0.50
     outlining
    0.50
     outline
    0.50
    Reader
    0.49
    Act Density 0.017%

    No Known Activations