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

    Neuronpedia

    INDEX
    Explanations

    religious commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भ्रष्टाचार
    0.77
     sweetness
    0.75
     encuentros
    0.73
     robustness
    0.71
     slander
    0.71
     honesty
    0.71
     generosity
    0.69
     eloquence
    0.69
    SecurityCenter
    0.68
     sayısı
    0.68
    POSITIVE LOGITS
     commands
    1.44
     Commands
    1.43
     command
    1.32
    Commands
    1.29
     Command
    1.29
     명령
    1.25
    commands
    1.25
     mandate
    1.20
    コマンド
    1.19
    Command
    1.18
    Act Density 0.010%

    No Known Activations