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

    Neuronpedia

    INDEX
    Explanations

    command line arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hampton
    0.90
    Mathematics
    0.88
    Teachers
    0.78
    hamton
    0.77
     physi
    0.74
     Phys
    0.73
     Physi
    0.72
     instituições
    0.72
    醛
    0.71
     Mathematics
    0.69
    POSITIVE LOGITS
     command
    2.97
    コマンド
    2.66
     Command
    2.61
    command
    2.60
     commands
    2.54
    Command
    2.49
     comando
    2.39
    命令行
    2.38
    命令
    2.38
     Commands
    2.25
    Act Density 1.266%

    No Known Activations