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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alv
    -0.08
    Chicken
    -0.07
    Invoice
    -0.07
    .mid
    -0.07
     occupants
    -0.07
    .balance
    -0.07
    	side
    -0.06
     Huntington
    -0.06
    拿了
    -0.06
     cum
    -0.06
    POSITIVE LOGITS
     OC
    0.08
     CONT
    0.07
     FAST
    0.07
     E
    0.07
    _FL
    0.07
     Agent
    0.07
    电脑
    0.07
     الفنان
    0.06
     AppDelegate
    0.06
    .FirstName
    0.06
    Act Density 0.002%

    No Known Activations