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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     everywhere
    -0.07
    icont
    -0.07
    说
    -0.07
     nz
    -0.06
    UEL
    -0.06
    .Details
    -0.06
     знать
    -0.06
     inquire
    -0.06
     careful
    -0.06
    nw
    -0.06
    POSITIVE LOGITS
     ACPI
    0.07
    умент
    0.07
    ″N
    0.07
    (Tile
    0.06
    _Float
    0.06
    ----------↵
    0.06
    ibli
    0.06
    etik
    0.06
     Cuba
    0.06
    .input
    0.06
    Act Density 0.006%

    No Known Activations