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

    Neuronpedia

    INDEX
    Explanations

    content related to energy production and its environmental impacts

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

    "coal," "power," and "plants"

    np_acts-logits-general · gemini-2.0-flash

    coal plants and power plants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعرف
    -0.65
    obium
    -0.57
     swar
    -0.56
    aterdag
    -0.56
     trow
    -0.53
    DataSnapshot
    -0.52
     tenda
    -0.52
    MethodManager
    -0.51
    setCharacter
    -0.51
     سما
    -0.51
    POSITIVE LOGITS
     plant
    1.07
     plants
    0.95
     coal
    0.94
     power
    0.87
    plant
    0.85
     Plant
    0.82
    coal
    0.82
     planta
    0.81
     nuclear
    0.79
     Plants
    0.78
    Act Density 0.223%

    No Known Activations