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

    Neuronpedia

    INDEX
    Explanations

    command and subcommand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atrium
    0.58
     QLabel
    0.46
     MES
    0.45
     protein
    0.40
    市場
    0.40
    Compensation
    0.40
     市場
    0.40
    🩰
    0.40
    細胞
    0.39
    設立
    0.39
    POSITIVE LOGITS
     command
    1.74
     commands
    1.66
    コマンド
    1.63
     명령
    1.56
     명령어
    1.56
    command
    1.55
    命令
    1.55
    Command
    1.52
     comando
    1.52
     subcommand
    1.52
    Act Density 0.016%

    No Known Activations