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

    Neuronpedia

    INDEX
    Explanations

    git subcommands and file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tables
    0.55
    DataTable
    0.55
    tables
    0.55
     tables
    0.51
    datatables
    0.49
    yaj
    0.48
     Select
    0.48
     DataTable
    0.47
     Live
    0.46
     Sweet
    0.46
    POSITIVE LOGITS
     рано
    0.39
    FBSDKApp
    0.36
     મોબ
    0.36
    訨
    0.36
     mocks
    0.36
    *}$
    0.36
    凖
    0.36
     bikers
    0.36
    Housing
    0.35
     accused
    0.35
    Act Density 0.027%

    No Known Activations