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

    Neuronpedia

    INDEX
    Explanations

    shell commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hampton
    0.88
    栋
    0.79
     KSI
    0.75
    hamton
    0.74
     دیا
    0.74
     சத்திய
    0.73
     ماده
    0.73
    সাহিত্য
    0.72
     ऑर्गे
    0.72
    semanticweb
    0.71
    POSITIVE LOGITS
     shell
    2.31
     command
    2.21
     Shell
    2.04
    Shell
    2.00
    コマンド
    1.99
    shell
    1.97
     commands
    1.95
     Command
    1.92
    command
    1.92
     shells
    1.89
    Act Density 1.342%

    No Known Activations