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

    Neuronpedia

    INDEX
    Explanations

    les

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Void
    -0.08
    .Location
    -0.07
    交融
    -0.07
    message
    -0.07
     linestyle
    -0.07
    =None
    -0.07
     HashMap
    -0.06
     FileInputStream
    -0.06
    .SECONDS
    -0.06
    done
    -0.06
    POSITIVE LOGITS
     emulator
    0.07
    楼主
    0.06
     현
    0.06
    طو
    0.06
    캬
    0.06
    얜
    0.06
     Mont
    0.06
     hiểu
    0.06
     củ
    0.06
     UAV
    0.06
    Act Density 0.556%

    No Known Activations