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

    Neuronpedia

    INDEX
    Explanations

    command line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     martens
    0.59
     Eindruck
    0.57
     Monster
    0.56
     Intelig
    0.56
     Agust
    0.55
     jugement
    0.55
     Delivering
    0.55
    憸
    0.55
     Vertical
    0.54
     Fingers
    0.54
    POSITIVE LOGITS
     命令
    0.90
    CMD
    0.88
     cmd
    0.88
    命令
    0.83
     cmds
    0.82
     comandos
    0.82
     Command
    0.79
    Commande
    0.79
     COMMAND
    0.78
    コマンド
    0.78
    Act Density 0.056%

    No Known Activations