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

    Neuronpedia

    INDEX
    Explanations

    calorie counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.46
     it
    0.45
     militia
    0.43
     totality
    0.42
    ိုလ်
    0.42
     cessation
    0.42
     commotion
    0.42
    inds
    0.42
     کھ
    0.42
     diameter
    0.41
    POSITIVE LOGITS
    叁章
    0.57
    вто
    0.57
    рел
    0.52
    том
    0.51
    рения
    0.50
    צוע
    0.48
    ления
    0.47
    лете
    0.47
     ПРО
    0.47
    ко
    0.46
    Act Density 0.005%

    No Known Activations