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

    Neuronpedia

    INDEX
    Explanations

    online text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentPage
    -0.07
     eigentlich
    -0.07
     wd
    -0.06
    	raw
    -0.06
     concludes
    -0.06
     bureauc
    -0.06
    ifferences
    -0.06
    (moment
    -0.06
     -(
    -0.06
    (room
    -0.06
    POSITIVE LOGITS
    emme
    0.07
     Comet
    0.07
    larıyla
    0.06
     Eduardo
    0.06
     чемпион
    0.06
    狂
    0.06
    击
    0.06
     goof
    0.06
     Estados
    0.06
    nie
    0.06
    Act Density 0.001%

    No Known Activations