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

    Neuronpedia

    INDEX
    Explanations

    simulated understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Preparation
    0.85
    Ready
    0.84
     Workflow
    0.83
    Prepare
    0.81
    Preparing
    0.77
     Preparation
    0.76
    เริ่มต้น
    0.76
    เพิ่มเติม
    0.75
    Planning
    0.74
    Prep
    0.74
    POSITIVE LOGITS
     impoverished
    0.93
     poverty
    0.90
     sucking
    0.88
     degradation
    0.87
     senescence
    0.87
     drunkenness
    0.86
     dictators
    0.86
     notoriously
    0.85
     immort
    0.85
     earthquakes
    0.85
    Act Density 0.597%

    No Known Activations