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

    Neuronpedia

    INDEX
    Explanations

    discovers villains or leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ecommerce
    0.98
    🕓
    0.96
    🏬
    0.96
     webinars
    0.92
    📙
    0.92
    🎑
    0.91
    🕔
    0.91
    🕕
    0.90
    📐
    0.90
    🚦
    0.89
    POSITIVE LOGITS
     Captain
    1.23
     Commander
    1.22
     Darth
    1.19
     King
    1.19
     Destroy
    1.19
     Lord
    1.16
     Evil
    1.15
     villain
    1.14
     Ancient
    1.13
     Death
    1.13
    Act Density 0.096%

    No Known Activations