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

    Neuronpedia

    INDEX
    Explanations

    definitions and specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FULLY
    0.56
    market
    0.53
    village
    0.53
    7
    0.52
    fully
    0.49
    try
    0.49
    GER
    0.49
    Material
    0.48
    time
    0.47
    ley
    0.47
    POSITIVE LOGITS
     tohoto
    0.48
     بما
    0.47
     headsets
    0.47
     historie
    0.46
     DJI
    0.46
     وجدت
    0.46
     komplex
    0.46
     séparation
    0.46
     आरमारा
    0.45
     wcex
    0.45
    Act Density 0.038%

    No Known Activations