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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sadece
    -0.06
     findings
    -0.06
     حداقل
    -0.06
     κατα
    -0.06
    470
    -0.06
    /AFP
    -0.06
     Producer
    -0.06
     Wag
    -0.06
     screws
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     HY
    0.08
     tribal
    0.06
     ав
    0.06
    lenmiş
    0.06
     JC
    0.06
    GU
    0.06
     NSDictionary
    0.06
    iliki
    0.06
     Chili
    0.06
    ोव
    0.06
    Act Density 0.070%

    No Known Activations