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

    Neuronpedia

    INDEX
    Explanations

    units of power and energy measurements

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

    units of power and energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     side
    -0.46
     Fische
    -0.42
     Hodges
    -0.42
     Jansen
    -0.40
    ╯
    -0.40
     taken
    -0.40
    PointerException
    -0.40
     Christiansen
    -0.39
     borders
    -0.39
     Rizzo
    -0.39
    POSITIVE LOGITS
     kW
    1.97
    kW
    1.94
     kilowatt
    1.43
    owatt
    1.25
    KW
    1.20
     kWh
    1.18
    kw
    1.14
    kWh
    1.13
     KW
    1.13
     kw
    1.08
    Act Density 0.003%

    No Known Activations