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

    Neuronpedia

    INDEX
    Explanations

    current state of affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibers
    0.43
    сион
    0.37
    Background
    0.37
    bbi
    0.37
    زيد
    0.37
    你知道
    0.36
    סף
    0.36
    Tara
    0.35
    opic
    0.35
    ciation
    0.35
    POSITIVE LOGITS
     things
    0.74
     Things
    0.64
     вещей
    0.64
    Things
    0.61
    things
    0.59
     चीजें
    0.55
     Dinge
    0.55
     affairs
    0.52
     चीजों
    0.51
     THINGS
    0.51
    Act Density 0.004%

    No Known Activations