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

    Neuronpedia

    INDEX
    Explanations

    un, nun

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Strength
    -0.07
    자가
    -0.06
     ca
    -0.06
    wayne
    -0.06
     показ
    -0.06
     дополнитель
    -0.06
     кли
    -0.06
    %",↵
    -0.06
     означа
    -0.06
    /features
    -0.06
    POSITIVE LOGITS
    unter
    0.07
     продолж
    0.07
    нії
    0.06
     Churches
    0.06
     Pose
    0.06
    delivery
    0.06
    ypse
    0.06
    	await
    0.06
    ось
    0.06
    ajax
    0.06
    Act Density 0.001%

    No Known Activations