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

    Neuronpedia

    INDEX
    Explanations

    product attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gespr
    0.78
     jealous
    0.78
     maps
    0.76
     부탁
    0.76
     proceeds
    0.74
     bolted
    0.73
     الطل
    0.73
     Congrats
    0.73
     equations
    0.73
     textos
    0.73
    POSITIVE LOGITS
    Brand
    0.82
     Brand
    0.80
    Country
    0.80
    MP
    0.76
    Item
    0.76
    Connectivity
    0.74
    country
    0.74
    region
    0.73
    Material
    0.73
    category
    0.73
    Act Density 0.031%

    No Known Activations