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

    Neuronpedia

    INDEX
    Explanations

    C# System namespace usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CONN
    0.40
    鉀
    0.39
     kanamycin
    0.39
     Sauna
    0.38
     ribosomes
    0.37
    ອອກ
    0.37
     orthogonality
    0.37
    椋
    0.37
    ASCADE
    0.36
    エリー
    0.36
    POSITIVE LOGITS
    Collections
    0.84
    Threading
    0.79
     collections
    0.71
    threading
    0.71
    Diagnostics
    0.70
    collections
    0.68
    Linq
    0.64
    IO
    0.63
     Collections
    0.63
    ComponentModel
    0.62
    Act Density 0.006%

    No Known Activations