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

    Neuronpedia

    INDEX
    Explanations

    routes and navigation components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rod
    0.49
    Plate
    0.46
    storybook
    0.44
    ri
    0.43
    l
    0.42
    Acetic
    0.42
    ボン
    0.41
    Asie
    0.41
    Hospital
    0.41
    EMPL
    0.41
    POSITIVE LOGITS
     calle
    0.43
     내
    0.43
     path
    0.42
     treaties
    0.42
     go
    0.41
    将
    0.41
    न्दावन
    0.40
     value
    0.40
     name
    0.40
     ইন্
    0.40
    Act Density 0.001%

    No Known Activations