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

    Neuronpedia

    INDEX
    Explanations

    flawed organism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gob
    0.38
    qualiter
    0.38
     iam
    0.38
     overs
    0.37
     বসে
    0.37
     gob
    0.37
     merkle
    0.36
    го
    0.36
    পাশ
    0.36
    迵
    0.36
    POSITIVE LOGITS
    istice
    0.41
    ildet
    0.40
    季節
    0.39
    esters
    0.38
    ]_{\
    0.38
    rides
    0.38
    enment
    0.37
     পাইল
    0.37
    買い
    0.37
    icides
    0.36
    Act Density 0.002%

    No Known Activations