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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quien
    -0.07
     besten
    -0.07
     政
    -0.07
     درخواست
    -0.07
    ออ
    -0.07
     Contest
    -0.07
     favored
    -0.07
     Reduce
    -0.07
     simplement
    -0.07
     Dent
    -0.06
    POSITIVE LOGITS
    (properties
    0.07
    dsn
    0.07
     %>
    0.06
    _chr
    0.06
    Sad
    0.06
    .setVisibility
    0.06
     Е
    0.06
    .categories
    0.06
    .SetText
    0.06
    setVisibility
    0.06
    Act Density 0.098%

    No Known Activations