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

    Neuronpedia

    INDEX
    Explanations

    genealogy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lun
    -0.07
    APO
    -0.07
    앙
    -0.07
     Stephanie
    -0.06
    .aws
    -0.06
    олько
    -0.06
     beet
    -0.06
    isz
    -0.06
     --------------------------------
    -0.06
     whe
    -0.06
    POSITIVE LOGITS
     accident
    0.06
     바랍니다
    0.06
    navigator
    0.06
    .pipeline
    0.06
    (Position
    0.06
     张
    0.06
     trưng
    0.06
     육
    0.06
     getState
    0.06
    	alert
    0.06
    Act Density 0.021%

    No Known Activations