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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妊娠
    -0.08
     Mus
    -0.07
    Expose
    -0.07
    เลย
    -0.07
     Mention
    -0.07
    惦
    -0.07
    蝶
    -0.07
    ceptive
    -0.07
    珍惜
    -0.07
     Soci
    -0.07
    POSITIVE LOGITS
    ,
    0.07
     состав
    0.07
    끅
    0.07
    🛣
    0.06
     ancor
    0.06
     מציע
    0.06
     всей
    0.06
    (draw
    0.06
     даль
    0.06
     narrow
    0.06
    Act Density 0.004%

    No Known Activations