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

    Neuronpedia

    INDEX
    Explanations

    Making decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aciones
    -0.06
     Beauty
    -0.06
    (root
    -0.06
     fathers
    -0.06
    ír
    -0.06
     cosmos
    -0.06
    ้าอ
    -0.06
     Items
    -0.06
    ette
    -0.06
     divorce
    -0.06
    POSITIVE LOGITS
    .dist
    0.06
    (gcf
    0.06
     앨
    0.06
     Gameplay
    0.06
    専
    0.06
     Ал
    0.06
    .sc
    0.06
    Bro
    0.06
    ��
    0.06
    оля
    0.06
    Act Density 0.102%

    No Known Activations