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

    Neuronpedia

    INDEX
    Explanations

    Year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �이
    -0.06
    orage
    -0.06
    .Signal
    -0.06
    )."
    -0.06
    694
    -0.06
    "While
    -0.06
     persec
    -0.06
     SWITCH
    -0.06
     Cooling
    -0.06
     breached
    -0.06
    POSITIVE LOGITS
    .references
    0.07
     Background
    0.06
     aplic
    0.06
     roku
    0.06
     Prize
    0.06
     Wifi
    0.06
    {},↵
    0.06
    /<?
    0.06
    ```
    0.06
     ipad
    0.06
    Act Density 0.017%

    No Known Activations