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

    Neuronpedia

    INDEX
    Explanations

    Re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enser
    -0.07
    霊
    -0.06
     comes
    -0.06
    actual
    -0.06
     ViewState
    -0.06
    ‌گ
    -0.06
     marg
    -0.06
    .Business
    -0.06
    케
    -0.06
     Cummings
    -0.06
    POSITIVE LOGITS
     resized
    0.07
    римін
    0.07
    pany
    0.07
    ประม
    0.07
     awarded
    0.06
     byla
    0.06
    )&&(
    0.06
    REQUIRED
    0.06
    	override
    0.06
    								
↵
    0.06
    Act Density 0.023%

    No Known Activations