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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _none
    -0.06
     timezone
    -0.06
     addObject
    -0.06
     �
    -0.06
    rams
    -0.06
     Parish
    -0.06
    		 ↵
    -0.06
     inverse
    -0.06
    283
    -0.06
    ственно
    -0.06
    POSITIVE LOGITS
     vy
    0.06
    ELL
    0.06
     natuur
    0.06
     attendees
    0.06
    ografie
    0.06
     وضعیت
    0.06
     ontvangst
    0.06
     mileage
    0.06
     omnip
    0.06
     scrim
    0.06
    Act Density 0.039%

    No Known Activations