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

    Neuronpedia

    INDEX
    Explanations

    debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     US
    -0.07
     blink
    -0.07
     دل
    -0.06
    oup
    -0.06
    .download
    -0.06
    ضان
    -0.06
     těchto
    -0.06
    един
    -0.06
    孤
    -0.06
    PopupMenu
    -0.06
    POSITIVE LOGITS
    이트
    0.07
     még
    0.07
     Loài
    0.06
     handling
    0.06
     filmpjes
    0.06
     eager
    0.06
    :E
    0.06
    Mage
    0.06
     HT
    0.06
    eton
    0.06
    Act Density 0.049%

    No Known Activations