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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /km
    -0.07
     آینده
    -0.06
     budouc
    -0.06
    IPS
    -0.06
    航空
    -0.06
    โจ
    -0.06
    firstname
    -0.06
     fanatic
    -0.06
    '],$
    -0.06
     smrt
    -0.06
    POSITIVE LOGITS
     cough
    0.07
    	Common
    0.07
     LinkedHashMap
    0.06
     unrest
    0.06
     ContentValues
    0.06
     RSVP
    0.06
     JsonResult
    0.06
    lice
    0.06
    (Content
    0.06
    <Props
    0.06
    Act Density 0.012%

    No Known Activations