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

    Neuronpedia

    INDEX
    Explanations

    There

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Persons
    -0.08
    킁
    -0.08
    慥
    -0.07
    erek
    -0.07
     Stephan
    -0.07
    	Get
    -0.07
     Cơ
    -0.07
     göz
    -0.07
     Tech
    -0.07
     Ann
    -0.06
    POSITIVE LOGITS
    lined
    0.08
     unsustainable
    0.07
     нашего
    0.07
     troubled
    0.07
    עלייה
    0.07
     rule
    0.07
    (Notification
    0.07
    sharing
    0.07
    $user
    0.07
    iation
    0.07
    Act Density 0.000%

    No Known Activations