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

    Neuronpedia

    INDEX
    Explanations

    list or table structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ст
    0.41
    LETIN
    0.40
     നമു
    0.40
    ProjectPath
    0.39
     apocalypse
    0.39
    식회사
    0.39
    роваться
    0.39
    чени
    0.39
    ImageLayout
    0.39
    лянчук
    0.39
    POSITIVE LOGITS
    *=
    0.56
    |
    0.54
    <table>
    0.54
     |
    0.54
     category
    0.53
     Legendary
    0.53
     Category
    0.52
     grouped
    0.52
     Categor
    0.50
     Legend
    0.49
    Act Density 0.002%

    No Known Activations