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

    Neuronpedia

    INDEX
    Explanations

    mathematical summation and integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    legt
    0.57
    ări
    0.51
     പതി
    0.50
     sebagian
    0.50
    ėjo
    0.49
    ardı
    0.49
    मि
    0.48
    ้าน
    0.48
    タル
    0.48
    ētu
    0.48
    POSITIVE LOGITS
     across
    0.54
     ergonomic
    0.51
     avanc
    0.51
     guarantee
    0.50
     [
    0.49
     four
    0.49
     innovation
    0.49
     -
    0.48
     Every
    0.48
     Animation
    0.47
    Act Density 0.001%

    No Known Activations