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

    Neuronpedia

    INDEX
    Explanations

    heat and its properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     allé
    0.42
     اقت
    0.42
     प्रच
    0.41
    اویر
    0.38
    三国
    0.37
     切り
    0.37
    昕
    0.37
    sized
    0.37
     sized
    0.37
    صوص
    0.36
    POSITIVE LOGITS
     generated
    0.78
     levels
    0.77
     gradient
    0.75
     emitted
    0.75
     exerted
    0.73
     gradients
    0.71
     transmitted
    0.68
     transmission
    0.68
     waves
    0.66
     emanating
    0.66
    Act Density 0.081%

    No Known Activations