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

    Neuronpedia

    INDEX
    Explanations

    table select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reinst
    -0.07
     bei
    -0.06
    $PostalCodesNL
    -0.06
    oproject
    -0.06
     dispozici
    -0.06
     unite
    -0.06
     battles
    -0.06
    urpose
    -0.06
     disdain
    -0.06
    POSE
    -0.06
    POSITIVE LOGITS
    ependency
    0.06
     vyžad
    0.06
    Что
    0.06
    恵
    0.06
    킨
    0.06
     aquarium
    0.06
    ้จ
    0.06
     объяс
    0.06
     ***/↵
    0.06
     cleaners
    0.06
    Act Density 0.010%

    No Known Activations