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

    Neuronpedia

    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /connect
    -0.07
    (Card
    -0.07
     Arm
    -0.07
     cardio
    -0.07
    .SIZE
    -0.06
    řila
    -0.06
     Cards
    -0.06
     GRAT
    -0.06
    اضر
    -0.06
    кої
    -0.06
    POSITIVE LOGITS
     box
    0.08
     intl
    0.06
    �
    0.06
    -ext
    0.06
     Box
    0.06
     vide
    0.06
    棚
    0.06
     fundraising
    0.06
    ='<?
    0.06
    suz
    0.06
    Act Density 0.007%

    No Known Activations