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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tab
    -0.07
    cede
    -0.07
     Packet
    -0.06
    tadır
    -0.06
     maker
    -0.06
     Kubernetes
    -0.06
     collector
    -0.06
    venue
    -0.06
    Win
    -0.06
     tracker
    -0.06
    POSITIVE LOGITS
    _sqrt
    0.08
    夢
    0.07
     тисяч
    0.07
     sexuales
    0.06
    orners
    0.06
     Bis
    0.06
    „To
    0.06
    umbo
    0.06
     усі
    0.06
     tarafından
    0.06
    Act Density 0.052%

    No Known Activations