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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to power generation and energy

    oai_token-act-pair · gemini-2.0-flash

    nuclear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ynchronously
    -0.68
     continúas
    -0.67
     ujednoznacz
    -0.66
     poffible
    -0.60
     betweenstory
    -0.60
    EDEFAULT
    -0.60
     Normdatei
    -0.60
    abello
    -0.59
    ükemmel
    -0.59
    دانشنامهٔ
    -0.59
    POSITIVE LOGITS
     nuclear
    0.60
     centrales
    0.57
    nuclear
    0.56
     Nuclear
    0.52
     Generating
    0.51
     nucléaire
    0.50
     NPP
    0.49
    Nuclear
    0.48
     Power
    0.48
     Unit
    0.47
    Act Density 0.604%

    No Known Activations