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

    Neuronpedia

    INDEX
    Explanations

    Acting/performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sequential
    -0.08
     mailbox
    -0.07
    泥
    -0.07
     grouping
    -0.07
     â
    -0.07
     sits
    -0.06
    ﾐ
    -0.06
    _centers
    -0.06
    Mur
    -0.06
    _ipc
    -0.06
    POSITIVE LOGITS
     Francisco
    0.06
    etSocketAddress
    0.06
    лаж
    0.06
    ח
    0.06
     Aless
    0.06
     Transformer
    0.06
     ع
    0.06
    Formatted
    0.06
    nez
    0.06
     """↵
    0.06
    Act Density 0.014%

    No Known Activations