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

    Neuronpedia

    INDEX
    Explanations

    classification and learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ob
    -0.07
     Sat
    -0.06
    ��
    -0.06
    urgical
    -0.06
    _deps
    -0.06
    важ
    -0.06
    obs
    -0.06
     Cars
    -0.06
     simulate
    -0.06
    (project
    -0.05
    POSITIVE LOGITS
    维
    0.07
    adoo
    0.07
    ocommerce
    0.06
    ‌ده
    0.06
    빠
    0.06
    xce
    0.06
    ยาน
    0.06
     Bylo
    0.06
    叶
    0.06
     mlad
    0.06
    Act Density 0.006%

    No Known Activations