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

    Neuronpedia

    INDEX
    Explanations

    budget-friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    німа
    0.68
    龔
    0.67
     Dhabi
    0.63
    atis
    0.63
    క్త
    0.62
    щее
    0.61
    瑚
    0.61
    न्तु
    0.59
     Nair
    0.59
    bellum
    0.58
    POSITIVE LOGITS
     berd
    0.66
     blown
    0.66
     नियु
    0.62
     ant
    0.61
    ори
    0.61
    vstack
    0.58
    aisen
    0.58
     Bowen
    0.58
     Trif
    0.58
     hard
    0.58
    Act Density 0.113%

    No Known Activations