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

    Neuronpedia

    INDEX
    Explanations

    command terminal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explicitly
    0.45
     RFID
    0.42
    <0x15>
    0.41
     refor
    0.41
     coales
    0.41
     unsigned
    0.41
     definitively
    0.41
     microfilm
    0.40
     নিরস্ত্র
    0.40
     unilaterally
    0.40
    POSITIVE LOGITS
    command
    0.83
     команд
    0.77
    Command
    0.74
    cmd
    0.73
     command
    0.71
    COMMAND
    0.70
    CMD
    0.68
     Command
    0.65
     comand
    0.62
     COMMAND
    0.62
    Act Density 0.055%

    No Known Activations