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

    Neuronpedia

    INDEX
    Explanations

    Locations, public spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dangerous
    -0.07
    確認
    -0.06
    .exc
    -0.06
    混
    -0.06
    .YEAR
    -0.06
     tiener
    -0.06
     Begins
    -0.06
     सन
    -0.06
    овер
    -0.06
     thoải
    -0.06
    POSITIVE LOGITS
    .bpm
    0.06
    888
    0.06
    /devices
    0.06
    coordinate
    0.06
    ated
    0.06
     quân
    0.06
    ale
    0.06
    (txt
    0.06
     behaviors
    0.06
    ATYPE
    0.06
    Act Density 0.081%

    No Known Activations