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

    Neuronpedia

    INDEX
    Explanations

    splitting up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exited
    -0.08
     Παν
    -0.07
     Cooling
    -0.06
    ظٹط
    -0.06
    -chief
    -0.06
    -tools
    -0.06
     Yet
    -0.06
    ��
    -0.06
     OPP
    -0.06
    vertisement
    -0.06
    POSITIVE LOGITS
    相信
    0.07
    ゴ
    0.06
    يدة
    0.06
    、新
    0.06
     třídy
    0.06
     jobject
    0.06
     gid
    0.06
     kinh
    0.06
    modx
    0.06
    rag
    0.06
    Act Density 0.005%

    No Known Activations