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

    Neuronpedia

    INDEX
    Explanations

    list items with descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.61
    8
    0.56
    :
    0.55
    ४
    0.54
    ถ
    0.52
    두
    0.52
     motorcycle
    0.52
    リン
    0.51
    7
    0.51
     林
    0.51
    POSITIVE LOGITS
     Tất
    0.59
     Éd
    0.54
    |_{\
    0.52
     Queries
    0.52
    playlists
    0.52
     Tạo
    0.52
    Blocks
    0.50
     वगैर
    0.50
    莢
    0.50
    јединачна
    0.50
    Act Density 0.000%

    No Known Activations