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

    Neuronpedia

    INDEX
    Explanations

    heat and temperature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pearl
    -0.08
     downloadable
    -0.07
    auro
    -0.07
    уға
    -0.07
     собра
    -0.07
     enumerable
    -0.07
     વિશ્વ
    -0.07
    dur
    -0.07
     irreversible
    -0.07
     infe
    -0.07
    POSITIVE LOGITS
     convection
    0.15
     turbulence
    0.11
     turbul
    0.10
     airflow
    0.10
     breeze
    0.09
     Celsius
    0.09
    空气
    0.09
     disturbances
    0.09
     swirling
    0.09
    凸
    0.09
    Act Density 0.022%

    No Known Activations