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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ольше
    -0.09
    ном
    -0.09
    акы
    -0.09
    ขั้นต่ำ
    -0.09
    ต้
    -0.08
    idzo
    -0.08
    র্ড
    -0.08
    ুধবার
    -0.08
     Folder
    -0.08
    992
    -0.08
    POSITIVE LOGITS
    产生
    0.10
     processes
    0.09
     sewage
    0.09
     inadvert
    0.09
     careless
    0.09
     veh
    0.09
     producing
    0.09
    生产
    0.08
     negligent
    0.08
    Processes
    0.08
    Act Density 0.027%

    No Known Activations