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

    Neuronpedia

    INDEX
    Explanations

    Describing memories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     продукции
    -0.08
    asper
    -0.08
    (global
    -0.08
     atá
    -0.07
     estrut
    -0.07
    ônicas
    -0.07
    adu
    -0.07
     sounding
    -0.07
     deseja
    -0.07
    plied
    -0.07
    POSITIVE LOGITS
    妹妹
    0.10
     solitude
    0.09
     sophomore
    0.09
     hikes
    0.08
    曾
    0.08
     souff
    0.08
     dinners
    0.08
     horseback
    0.08
     unforgettable
    0.08
     hiking
    0.08
    Act Density 0.035%

    No Known Activations