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

    Neuronpedia

    INDEX
    Explanations

    JSON structures and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    um
    0.51
    łoś
    0.47
    ul
    0.46
    ť
    0.46
    ர
    0.46
    ج
    0.44
    oe
    0.44
    лья
    0.44
    ľov
    0.44
    it
    0.44
    POSITIVE LOGITS
    ஒரு
    0.47
    新たに
    0.46
    datatype
    0.45
    DbType
    0.44
     {/*
    0.44
    雇用
    0.44
    Incorpor
    0.43
    yscraper
    0.43
     construe
    0.43
    Movies
    0.42
    Act Density 0.006%

    No Known Activations