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

    Neuronpedia

    INDEX
    Explanations

    instructions related to managing energy consumption or power usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following commands to turn something on or off

    np_acts-logits-general · gemini-2.0-flash

    turn on lights or turn off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.86
    contentLoaded
    -0.67
    XtraBars
    -0.61
     intptr
    -0.56
     Presbyter
    -0.56
    taxia
    -0.55
     estimés
    -0.54
    üyada
    -0.53
    writeFieldEnd
    -0.52
    msford
    -0.52
    POSITIVE LOGITS
     lights
    0.85
     luces
    0.65
     chauffage
    0.64
     Lights
    0.64
     heater
    0.63
    Lights
    0.63
    lights
    0.62
    ViewImports
    0.60
     engines
    0.58
     sprink
    0.58
    Act Density 0.265%

    No Known Activations