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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    in
    -0.10
    en
    -0.08
    ин
    -0.08
    etin
    -0.08
    i
    -0.08
    un
    -0.08
    o
    -0.07
    em
    -0.07
    an
    -0.07
    unding
    -0.07
    POSITIVE LOGITS
    ":
    0.08
    ",
    0.08
    )":
    0.08
    %@",
    0.08
    .”
    0.07
    ,’”
    0.07
    ']}'
    0.07
    :@"%@",
    0.07
    )",
    0.07
    ”?
    0.07
    Act Density 0.677%

    No Known Activations