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

    Neuronpedia

    INDEX
    Explanations

    document data and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rah
    0.41
     ສຳ
    0.40
    Anti
    0.39
     Integr
    0.38
    BOOLE
    0.37
     Gandh
    0.37
     интегра
    0.37
     Bode
    0.36
    缓慢
    0.36
    Integr
    0.36
    POSITIVE LOGITS
     doc
    0.51
     export
    0.51
    doc
    0.48
     import
    0.46
     effect
    0.43
     Doc
    0.43
    onal
    0.41
     defined
    0.40
     docs
    0.40
     Lindsay
    0.40
    Act Density 0.008%

    No Known Activations